diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..c0bf21263f91f79f840f6ebfa2d8fcbcb3d43066 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +miku.png filter=lfs diff=lfs merge=lfs -text +uvr5_models/Demucs/04573f0d-f3cf25b2.th filter=lfs diff=lfs merge=lfs -text +uvr5_models/Demucs/92cfc3b6-ef3bcb9c.th filter=lfs diff=lfs merge=lfs -text +uvr5_models/Demucs/955717e8-8726e21a.th filter=lfs diff=lfs merge=lfs -text +uvr5_models/Demucs/d12395a8-e57c48e6.th filter=lfs diff=lfs merge=lfs -text +uvr5_models/Demucs/f7e0c4bc-ba3fe64a.th filter=lfs diff=lfs merge=lfs -text +uvr5_models/Demucs/5c90dfd2-34c22ccb.th filter=lfs diff=lfs merge=lfs -text +uvr5_models/Demucs/75fc33f5-1941ce65.th filter=lfs diff=lfs merge=lfs -text +ffmpeg/ffmpeg.exe filter=lfs diff=lfs merge=lfs -text +ffmpeg/ffprobe.exe filter=lfs diff=lfs merge=lfs -text +ico.png filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..7b418cf3c4f9513d60157307055d200a485def2a --- /dev/null +++ b/README.md @@ -0,0 +1,349 @@ +--- +license: mit +language: +- vi +- en +pipeline_tag: audio-to-audio +tags: +- RVC +- VITS +- VC +- Voice Conversion +base_model: +- lj1995/VoiceConversionWebUI +- IAHispano/Applio +- cvssp/audioldm2 +- cvssp/audioldm2-music +- cvssp/audioldm2-large +- speechbrain/spkrec-ecapa-voxceleb +--- + +
+
+# Vietnamese RVC BY ANH
+Công cụ chuyển đổi giọng nói chất lượng và hiệu suất cao đơn giản dành cho người Việt.
+
+[](https://github.com/PhamHuynhAnh16/Vietnamese-RVC)
+[](https://colab.research.google.com/github/PhamHuynhAnh16/Vietnamese-RVC-ipynb/blob/main/Vietnamese-RVC.ipynb)
+[](https://github.com/PhamHuynhAnh16/Vietnamese-RVC/blob/main/LICENSE)
+
++Vietnamese-RVC-main +├── assets +│ ├── f0 +│ ├── languages +│ │ ├── en-US.json +│ │ └── vi-VN.json +│ ├── logs +│ │ └── mute +│ │ ├── f0 +│ │ │ └── mute.wav.npy +│ │ ├── f0_voiced +│ │ │ └── mute.wav.npy +│ │ ├── sliced_audios +│ │ │ ├── mute32000.wav +│ │ │ ├── mute40000.wav +│ │ │ └── mute48000.wav +│ │ ├── sliced_audios_16k +│ │ │ └── mute.wav +│ │ ├── v1_extracted +│ │ │ ├── mute.npy +│ │ │ └── mute_spin.npy +│ │ └── v2_extracted_spin +│ │ ├── mute.npy +│ │ └── mute_spin.npy +│ ├── models +│ │ ├── audioldm2 +│ │ ├── embedders +│ │ ├── predictors +│ │ ├── pretrained_custom +│ │ ├── pretrained_v1 +│ │ ├── pretrained_v2 +│ │ ├── speaker_diarization +│ │ │ ├── assets +│ │ │ │ ├── gpt2.tiktoken +│ │ │ │ ├── mel_filters.npz +│ │ │ │ └── multilingual.tiktoken +│ │ │ └── models +│ │ └── uvr5 +│ ├── presets +│ ├── weights +│ └── ico.png +├── audios +├── dataset +├── main +│ ├── app +│ │ ├── app.py +│ │ ├── tensorboard.py +│ │ └── parser.py +│ ├── configs +│ │ ├── v1 +│ │ │ ├── 32000.json +│ │ │ ├── 40000.json +│ │ │ └── 48000.json +│ │ ├── v2 +│ │ │ ├── 32000.json +│ │ │ ├── 40000.json +│ │ │ └── 48000.json +│ │ ├── config.json +│ │ └── config.py +│ ├── inference +│ │ ├── audio_effects.py +│ │ ├── audioldm2.py +│ │ ├── convert.py +│ │ ├── create_dataset.py +│ │ ├── create_index.py +│ │ ├── extract.py +│ │ ├── preprocess.py +│ │ ├── separator_music.py +│ │ └── train.py +│ ├── library +│ │ ├── algorithm +│ │ │ ├── commons.py +│ │ │ ├── modules.py +│ │ │ ├── mrf_hifigan.py +│ │ │ ├── onnx_export.py +│ │ │ ├── refinegan.py +│ │ │ ├── residuals.py +│ │ │ ├── separator.py +│ │ │ └── stftpitchshift.py +│ │ ├── architectures +│ │ │ ├── demucs_separator.py +│ │ │ ├── fairseq.py +│ │ │ └── mdx_separator.py +│ │ ├── audioldm2 +│ │ │ ├── models.py +│ │ │ └── utils.py +│ │ ├── predictors +│ │ │ ├── CREPE.py +│ │ │ ├── FCPE.py +│ │ │ ├── Generator.py +│ │ │ ├── RMVPE.py +│ │ │ ├── SWIPE.py +│ │ │ └── WORLD_WRAPPER.py +│ │ ├── speaker_diarization +│ │ │ ├── audio.py +│ │ │ ├── ECAPA_TDNN.py +│ │ │ ├── embedding.py +│ │ │ ├── encoder.py +│ │ │ ├── features.py +│ │ │ ├── parameter_transfer.py +│ │ │ ├── segment.py +│ │ │ ├── speechbrain.py +│ │ │ └── whisper.py +│ │ ├── uvr5_separator +│ │ │ ├── common_separator.py +│ │ │ ├── spec_utils.py +│ │ │ └── demucs +│ │ │ ├── apply.py +│ │ │ ├── demucs.py +│ │ │ ├── hdemucs.py +│ │ │ ├── htdemucs.py +│ │ │ ├── states.py +│ │ │ └── utils.py +│ │ └── utils.py +│ └── tools +│ ├── gdown.py +│ ├── huggingface.py +│ ├── mediafire.py +│ ├── meganz.py +│ ├── noisereduce.py +│ └── pixeldrain.py +├── docker-compose-cpu.yaml +├── docker-compose-cuda118.yaml +├── docker-compose-cuda128.yaml +├── Dockerfile +├── Dockerfile.cuda118 +├── Dockerfile.cuda128 +├── LICENSE +├── README.md +├── requirements.txt +├── run_app.bat +└── tensorboard.bat ++ +# LƯU Ý + +- **Dự án này chỉ hỗ trợ trên gpu của NVIDIA (Có thể sẽ hỗ trợ AMD sau nếu tôi có gpu AMD để thử)** +- **Hiện tại các bộ mã hóa mới như MRF HIFIGAN vẫn chưa đầy đủ các bộ huấn luyện trước** +- **Bộ mã hóa MRF HIFIGAN và REFINEGAN không hỗ trợ huấn luyện khi không không huấn luyện cao độ** +- **Các mô hình trong kho lưu trữ Vietnamese-RVC được thu thập rải rác trên AI Hub, HuggingFace và các các kho lưu trữ khác. Có thể mang các giấy phép bản quyền khác nhau (Ví dụ: Audioldm2 có các trọng số mô hình với điều khoản "Phi Thương Mại")** +- **Mã nguồn này có chứa thành phần phần mềm bên thứ ba được cấp phép với điều khoản "phi thương mại". Bất kỳ hành vi sử dụng thương mại nào, bao gồm kêu gọi tài trợ hoặc tài chính hóa phần mềm phái sinh, đều có thể vi phạm giấy phép và sẽ phải chịu trách nhiệm pháp lý tương ứng.** + +# Điều khoản sử dụng + +- Bạn phải đảm bảo rằng các nội dung âm thanh bạn tải lên và chuyển đổi qua dự án này không vi phạm quyền sở hữu trí tuệ của bên thứ ba. + +- Không được phép sử dụng dự án này cho bất kỳ hoạt động nào bất hợp pháp, bao gồm nhưng không giới hạn ở việc sử dụng để lừa đảo, quấy rối, hay gây tổn hại đến người khác. + +- Bạn chịu trách nhiệm hoàn toàn đối với bất kỳ thiệt hại nào phát sinh từ việc sử dụng sản phẩm không đúng cách. + +- Tôi sẽ không chịu trách nhiệm với bất kỳ thiệt hại trực tiếp hoặc gián tiếp nào phát sinh từ việc sử dụng dự án này. + +# Dự án này được xây dựng dựa trên các dự án như sau + +| Tác Phẩm | Tác Giả | Giấy Phép | +|--------------------------------------------------------------------------------------------------------------------------------|-------------------------|-------------| +| **[Applio](https://github.com/IAHispano/Applio/tree/main)** | IAHispano | MIT License | +| **[Python-audio-separator](https://github.com/nomadkaraoke/python-audio-separator/tree/main)** | Nomad Karaoke | MIT License | +| **[Retrieval-based-Voice-Conversion-WebUI](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/tree/main)** | RVC Project | MIT License | +| **[RVC-ONNX-INFER-BY-Anh](https://github.com/PhamHuynhAnh16/RVC_Onnx_Infer)** | Phạm Huỳnh Anh | MIT License | +| **[Torch-Onnx-Crepe-By-Anh](https://github.com/PhamHuynhAnh16/TORCH-ONNX-CREPE)** | Phạm Huỳnh Anh | MIT License | +| **[Hubert-No-Fairseq](https://github.com/PhamHuynhAnh16/hubert-no-fairseq)** | Phạm Huỳnh Anh | MIT License | +| **[Local-attention](https://github.com/lucidrains/local-attention)** | Phil Wang | MIT License | +| **[TorchFcpe](https://github.com/CNChTu/FCPE/tree/main)** | CN_ChiTu | MIT License | +| **[FcpeONNX](https://github.com/deiteris/voice-changer/blob/master-custom/server/utils/fcpe_onnx.py)** | Yury | MIT License | +| **[ContentVec](https://github.com/auspicious3000/contentvec)** | Kaizhi Qian | MIT License | +| **[Mediafiredl](https://github.com/Gann4Life/mediafiredl)** | Santiago Ariel Mansilla | MIT License | +| **[Noisereduce](https://github.com/timsainb/noisereduce)** | Tim Sainburg | MIT License | +| **[World.py-By-Anh](https://github.com/PhamHuynhAnh16/world.py)** | Phạm Huỳnh Anh | MIT License | +| **[Mega.py](https://github.com/3v1n0/mega.py)** | Marco Trevisan | No License | +| **[Gdown](https://github.com/wkentaro/gdown)** | Kentaro Wada | MIT License | +| **[Whisper](https://github.com/openai/whisper)** | OpenAI | MIT License | +| **[PyannoteAudio](https://github.com/pyannote/pyannote-audio)** | pyannote | MIT License | +| **[AudioEditingCode](https://github.com/HilaManor/AudioEditingCode)** | Hila Manor | MIT License | +| **[StftPitchShift](https://github.com/jurihock/stftPitchShift)** | Jürgen Hock | MIT License | +| **[Codename-RVC-Fork-3](https://github.com/codename0og/codename-rvc-fork-3)** | Codename;0 | MIT License | + +# Kho mô hình của công cụ tìm kiếm mô hình + +- **[VOICE-MODELS.COM](https://voice-models.com/)** + +# Các phương pháp trích xuất Pitch trong RVC + +Tài liệu này trình bày chi tiết các phương pháp trích xuất cao độ được sử dụng, thông tin về ưu, nhược điểm, sức mạnh và độ tin cậy của từng phương pháp theo trải nghiệm cá nhân. + +| Phương pháp | Loại | Ưu điểm | Hạn chế | Sức mạnh | Độ tin cậy | +|--------------------|----------------|---------------------------|------------------------------|--------------------|--------------------| +| pm | Praat | Nhanh | Kém chính xác | Thấp | Thấp | +| dio | PYWORLD | Thích hợp với Rap | Kém chính xác với tần số cao | Trung bình | Trung bình | +| harvest | PYWORLD | Chính xác hơn DIO | Xử lý chậm hơn | Cao | Rất cao | +| crepe | Deep Learning | Chính xác cao | Yêu cầu GPU | Rất cao | Rất cao | +| mangio-crepe | crepe finetune | Tối ưu hóa cho RVC | Đôi khi kém crepe gốc | Trung bình đến cao | Trung bình đến cao | +| fcpe | Deep Learning | Chính xác, thời gian thực | Cần GPU mạnh | Khá | Trung bình | +| fcpe-legacy | Old | Chính xác, thời gian thực | Cũ hơn | Khá | Trung bình | +| rmvpe | Deep Learning | Hiệu quả với giọng hát | Tốn tài nguyên | Rất cao | Xuất sắc | +| rmvpe-legacy | Old | Hỗ trợ hệ thống cũ | Cũ hơn | Cao | Khá | +| yin | Librosa | Đơn giản, hiệu quả | Dễ lỗi bội | Trung bình | Thấp | +| pyin | Librosa | Ổn định hơn YIN | Tính toán phức tạp hơn | Khá | Khá | +| swipe | WORLD | Độ chính xác cao | Nhạy cảm với nhiễu | Cao | Khá | + +# Báo cáo lỗi + +- **Với trường hợp gặp lỗi khi sử dụng mã nguồn này tôi thực sự xin lỗi bạn vì trải nghiệm không tốt này, bạn có thể gửi báo cáo lỗi thông qua cách phía dưới** +- **Bạn có thể báo cáo lỗi cho tôi thông qua hệ thống báo cáo lỗi webhook trong giao diện sử dụng** +- **Với trường hợp hệ thống báo cáo lỗi không hoạt động bạn có thể báo cáo lỗi cho tôi thông qua Discord `pham_huynh_anh` Hoặc [ISSUE](https://github.com/PhamHuynhAnh16/Vietnamese-RVC/issues)** + +# ☎️ Liên hệ tôi +- Discord: **pham_huynh_anh** \ No newline at end of file diff --git a/binary/decrypt.bin b/binary/decrypt.bin new file mode 100644 index 0000000000000000000000000000000000000000..85da68557da0749d6532388eab083cdfea3de416 --- /dev/null +++ b/binary/decrypt.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:330268cbf6b9317a76510b533e1640ef48ed074a07c013e5b1abc4d48cfd9dce +size 32 diff --git a/binary/world.bin b/binary/world.bin new file mode 100644 index 0000000000000000000000000000000000000000..842369e52d3603ad28142d6c0a99422f9d95166f --- /dev/null +++ b/binary/world.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49520c26e725e1d71a4ee4361fd1e41a12ec67b59912821f5123dce6eb572c16 +size 3481870 diff --git a/embedders/fairseq/chinese_hubert_base.pt b/embedders/fairseq/chinese_hubert_base.pt new file mode 100644 index 0000000000000000000000000000000000000000..ee11bf471f035ac8178a874bf19565abf22c92e4 --- /dev/null +++ b/embedders/fairseq/chinese_hubert_base.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cd5db6302ae2e79b5972cd02ae375a42a76170374d6e1952fa78d1fe4e4f756 +size 1136482241 diff --git a/embedders/fairseq/contentvec_base.pt b/embedders/fairseq/contentvec_base.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a2f13fb9c7047dff746e2d5d88c0d0a5aecf643 --- /dev/null +++ b/embedders/fairseq/contentvec_base.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60d936ec5a566776fc392e69ad8b630d14eb588111233fe313436e200a7b187b +size 1330114945 diff --git a/embedders/fairseq/hubert_base.pt b/embedders/fairseq/hubert_base.pt new file mode 100644 index 0000000000000000000000000000000000000000..72f47ab58564f01d5cc8b05c63bdf96d944551ff --- /dev/null +++ b/embedders/fairseq/hubert_base.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f54b40fd2802423a5643779c4861af1e9ee9c1564dc9d32f54f20b5ffba7db96 +size 189507909 diff --git a/embedders/fairseq/japanese_hubert_base.pt b/embedders/fairseq/japanese_hubert_base.pt new file mode 100644 index 0000000000000000000000000000000000000000..e32292b1e3318259ec0d56c6c646f6a82064b2ba --- /dev/null +++ b/embedders/fairseq/japanese_hubert_base.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dade3cf824ae0d214f7de8b73e70bae7c101e81f12d93577c4760bf516db4063 +size 378888853 diff --git a/embedders/fairseq/korean_hubert_base.pt b/embedders/fairseq/korean_hubert_base.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf13a33f4f8fa20105283d0e64ced545bd8bb023 --- /dev/null +++ b/embedders/fairseq/korean_hubert_base.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b42c8453b96b203198c1c280a8821158ea3fa8dbbc2a6220cad1c1489c3e65e +size 378876997 diff --git a/embedders/fairseq/portuguese_hubert_base.pt b/embedders/fairseq/portuguese_hubert_base.pt new file mode 100644 index 0000000000000000000000000000000000000000..208cbac6582c3b50a77ebbfe44b7a8bae2dd6a5f --- /dev/null +++ b/embedders/fairseq/portuguese_hubert_base.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c470a15cfcf6e2452c4c293481f0ccd208d22c58c8fa777c3c01afe9753c7797 +size 1134934506 diff --git a/embedders/fairseq/vietnamese_hubert_base.pt b/embedders/fairseq/vietnamese_hubert_base.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d2f4dbade2811269ac150f5f2521309de6ce264 --- /dev/null +++ b/embedders/fairseq/vietnamese_hubert_base.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ff575e6b56f6340ceaf5851810b714b8b65cace61d6bcb4f2c0765f7f4b2eb +size 378901471 diff --git a/embedders/onnx/chinese_hubert_base.onnx b/embedders/onnx/chinese_hubert_base.onnx new file mode 100644 index 0000000000000000000000000000000000000000..5fe7e74fa9a2985e7134f3d6d6dd2c8c0b87864a --- /dev/null +++ b/embedders/onnx/chinese_hubert_base.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8c53505aac5eb11dd7e0f63ed9ad3832eab1a264e4a99e11e6945e606575aa5 +size 378525322 diff --git a/embedders/onnx/contentvec_base.onnx b/embedders/onnx/contentvec_base.onnx new file mode 100644 index 0000000000000000000000000000000000000000..9126dff49b255793cdc85a874bc5f059460db7df --- /dev/null +++ b/embedders/onnx/contentvec_base.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a9dec116a03ce7a01ead3def93067b03a580e1fa78a60440fe08488f25a60f0 +size 378525322 diff --git a/embedders/onnx/hubert_base.onnx b/embedders/onnx/hubert_base.onnx new file mode 100644 index 0000000000000000000000000000000000000000..9126dff49b255793cdc85a874bc5f059460db7df --- /dev/null +++ b/embedders/onnx/hubert_base.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a9dec116a03ce7a01ead3def93067b03a580e1fa78a60440fe08488f25a60f0 +size 378525322 diff --git a/embedders/onnx/japanese_hubert_base.onnx b/embedders/onnx/japanese_hubert_base.onnx new file mode 100644 index 0000000000000000000000000000000000000000..5f880d0032717c22fb0b3054de2e7548b45a484a --- /dev/null +++ b/embedders/onnx/japanese_hubert_base.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9440863e042f6106e714f52fd17e707f8ba3c1d92e5e2da892c22ed384e6210 +size 378525322 diff --git a/embedders/onnx/korean_hubert_base.onnx b/embedders/onnx/korean_hubert_base.onnx new file mode 100644 index 0000000000000000000000000000000000000000..ab4958e7daa18a5dde3a9af4f93a18161ed2da53 --- /dev/null +++ b/embedders/onnx/korean_hubert_base.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0ebd55e5367096f9f56bb51ca4021a0f23fa1f4c007564a932589820ba0255c +size 378519741 diff --git a/embedders/onnx/portuguese_hubert_base.onnx b/embedders/onnx/portuguese_hubert_base.onnx new file mode 100644 index 0000000000000000000000000000000000000000..784864a86216ed4d321014dc943b3d8edfc0a0d1 --- /dev/null +++ b/embedders/onnx/portuguese_hubert_base.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2808488aee9e72abbcd1145eba9a4c8a93f554b8b1a2d1536a4b8cbcd195544e +size 378525322 diff --git a/embedders/onnx/vietnamese_hubert_base.onnx b/embedders/onnx/vietnamese_hubert_base.onnx new file mode 100644 index 0000000000000000000000000000000000000000..dec486805ffb1874655c032ef46b047f77e09940 --- /dev/null +++ b/embedders/onnx/vietnamese_hubert_base.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4584d4f967ef26e9e9d2c66af3484ac8b0c10d1c04bdc8fa550039e17dc294c3 +size 378525322 diff --git a/embedders/spin/spin-v1/config.json b/embedders/spin/spin-v1/config.json new file mode 100644 index 0000000000000000000000000000000000000000..787124b72efac92eda06941d2b3a36f096820a86 --- /dev/null +++ b/embedders/spin/spin-v1/config.json @@ -0,0 +1,71 @@ +{ + "activation_dropout": 0.1, + "apply_spec_augment": true, + "architectures": [ + "HubertModelWithFinalProj" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": true, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 12, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.44.2", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/embedders/spin/spin-v1/model.safetensors b/embedders/spin/spin-v1/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6ac0bde96c3600b9069fd8f474d57c3afa61318e --- /dev/null +++ b/embedders/spin/spin-v1/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fbe5252ec915b1ea3ff58836c974d5cccf6b0cbb0365c9a1a4b66ed5b0448b5 +size 378298232 diff --git a/embedders/spin/spin-v1/pytorch_model.bin b/embedders/spin/spin-v1/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..58b4f5101f8561f3658a1dd97e8f249dfbfe5e23 --- /dev/null +++ b/embedders/spin/spin-v1/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:057f12bfda54e2d486d86a52a3beb2a07c96a888bc6ac0c382c12ac18dbd500c +size 378356791 diff --git a/embedders/spin/spin-v2/config.json b/embedders/spin/spin-v2/config.json new file mode 100644 index 0000000000000000000000000000000000000000..5a86e3b44fe9b3b16f265204eeb3cf64afefceaf --- /dev/null +++ b/embedders/spin/spin-v2/config.json @@ -0,0 +1,72 @@ +{ + "activation_dropout": 0.1, + "apply_spec_augment": true, + "architectures": [ + "HubertModelWithFinalProj" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_pos_batch_norm": false, + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": true, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 12, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.55.0", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/embedders/spin/spin-v2/model.safetensors b/embedders/spin/spin-v2/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ea15d4e2df2615e73a03cc9541627b29b3ea3699 --- /dev/null +++ b/embedders/spin/spin-v2/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf87f2dc5190175c38d0dabf5ec22186ad37e727b162a1657e0c2577ad29d8d4 +size 378298232 diff --git a/embedders/spin/spin-v2/pytorch_model.bin b/embedders/spin/spin-v2/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..f1fcd1c9352846f6330d6a215f1bbefa3a8d39cd --- /dev/null +++ b/embedders/spin/spin-v2/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a9ac0be326057b17607a988be497793817f8274e987cf691a1b61192510f823 +size 378356791 diff --git a/embedders/transformers/chinese_hubert_base/config.json b/embedders/transformers/chinese_hubert_base/config.json new file mode 100644 index 0000000000000000000000000000000000000000..c876d5034cc79c2eb9bd569d21c7866fa43701dc --- /dev/null +++ b/embedders/transformers/chinese_hubert_base/config.json @@ -0,0 +1,72 @@ +{ + "activation_dropout": 0.1, + "apply_spec_augment": true, + "architectures": [ + "HubertModelWithFinalProj" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_pos_batch_norm": false, + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": true, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 12, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.48.3", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/embedders/transformers/chinese_hubert_base/model.safetensors b/embedders/transformers/chinese_hubert_base/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9e311b6dd48325a5742f58b5db9fff9fa6d0b2a5 --- /dev/null +++ b/embedders/transformers/chinese_hubert_base/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc3fa60ed3745b9e488e253df050faf7bc800c58b454ce50fafa7b98cef1de34 +size 378298264 diff --git a/embedders/transformers/chinese_hubert_base/pytorch_model.bin b/embedders/transformers/chinese_hubert_base/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..621bf852fc1c20112ee9fa4219feea594005f8ab --- /dev/null +++ b/embedders/transformers/chinese_hubert_base/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e392525e7948cbc595255f687902926c50d6fa46423255ab437b7ceb59de003 +size 378356318 diff --git a/embedders/transformers/contentvec_base/config.json b/embedders/transformers/contentvec_base/config.json new file mode 100644 index 0000000000000000000000000000000000000000..c876d5034cc79c2eb9bd569d21c7866fa43701dc --- /dev/null +++ b/embedders/transformers/contentvec_base/config.json @@ -0,0 +1,72 @@ +{ + "activation_dropout": 0.1, + "apply_spec_augment": true, + "architectures": [ + "HubertModelWithFinalProj" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_pos_batch_norm": false, + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": true, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 12, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.48.3", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/embedders/transformers/contentvec_base/model.safetensors b/embedders/transformers/contentvec_base/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cda2297949a39ca12d2f748278c95fa9d12b08e9 --- /dev/null +++ b/embedders/transformers/contentvec_base/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6acc85cc132c913188652d408ba1995f192e08a3090767a082ed3ff56897ab3 +size 378298264 diff --git a/embedders/transformers/contentvec_base/pytorch_model.bin b/embedders/transformers/contentvec_base/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..29eac6d27a42083f385e029ec14fa112bb1ea7ee --- /dev/null +++ b/embedders/transformers/contentvec_base/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f6798d68e2f4f9d99889eda8178566153bfe0894b4d16789b965b2c4cfb8a2c +size 378356318 diff --git a/embedders/transformers/hubert_base/config.json b/embedders/transformers/hubert_base/config.json new file mode 100644 index 0000000000000000000000000000000000000000..c876d5034cc79c2eb9bd569d21c7866fa43701dc --- /dev/null +++ b/embedders/transformers/hubert_base/config.json @@ -0,0 +1,72 @@ +{ + "activation_dropout": 0.1, + "apply_spec_augment": true, + "architectures": [ + "HubertModelWithFinalProj" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_pos_batch_norm": false, + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": true, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 12, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.48.3", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/embedders/transformers/hubert_base/model.safetensors b/embedders/transformers/hubert_base/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cda2297949a39ca12d2f748278c95fa9d12b08e9 --- /dev/null +++ b/embedders/transformers/hubert_base/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6acc85cc132c913188652d408ba1995f192e08a3090767a082ed3ff56897ab3 +size 378298264 diff --git a/embedders/transformers/hubert_base/pytorch_model.bin b/embedders/transformers/hubert_base/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..29eac6d27a42083f385e029ec14fa112bb1ea7ee --- /dev/null +++ b/embedders/transformers/hubert_base/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f6798d68e2f4f9d99889eda8178566153bfe0894b4d16789b965b2c4cfb8a2c +size 378356318 diff --git a/embedders/transformers/japanese_hubert_base/config.json b/embedders/transformers/japanese_hubert_base/config.json new file mode 100644 index 0000000000000000000000000000000000000000..c876d5034cc79c2eb9bd569d21c7866fa43701dc --- /dev/null +++ b/embedders/transformers/japanese_hubert_base/config.json @@ -0,0 +1,72 @@ +{ + "activation_dropout": 0.1, + "apply_spec_augment": true, + "architectures": [ + "HubertModelWithFinalProj" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_pos_batch_norm": false, + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": true, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 12, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.48.3", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/embedders/transformers/japanese_hubert_base/model.safetensors b/embedders/transformers/japanese_hubert_base/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c07363cb429176c8f31c698765cada458a3faa5e --- /dev/null +++ b/embedders/transformers/japanese_hubert_base/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7083ebdbd2650d0c5c5a34f84c931fb62018918614a68c5c5a503a319f8e3e8 +size 378298264 diff --git a/embedders/transformers/japanese_hubert_base/pytorch_model.bin b/embedders/transformers/japanese_hubert_base/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..8dbfe3793f62d7aefab99201c2978dfd77e44563 --- /dev/null +++ b/embedders/transformers/japanese_hubert_base/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83781c5d9e4fd355bbe00406047c847812afa0c54c843e4f349cd33c5baaa8b4 +size 378356318 diff --git a/embedders/transformers/korean_hubert_base/config.json b/embedders/transformers/korean_hubert_base/config.json new file mode 100644 index 0000000000000000000000000000000000000000..c876d5034cc79c2eb9bd569d21c7866fa43701dc --- /dev/null +++ b/embedders/transformers/korean_hubert_base/config.json @@ -0,0 +1,72 @@ +{ + "activation_dropout": 0.1, + "apply_spec_augment": true, + "architectures": [ + "HubertModelWithFinalProj" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_pos_batch_norm": false, + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": true, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 12, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.48.3", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/embedders/transformers/korean_hubert_base/model.safetensors b/embedders/transformers/korean_hubert_base/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ce3d055f693dd35eedb0186f5990e2fc7869c50c --- /dev/null +++ b/embedders/transformers/korean_hubert_base/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dfa6865dc4ea4f1dde7d87d10007178a95c1c0c586e6223cbbcb86b1c72d010 +size 378298264 diff --git a/embedders/transformers/korean_hubert_base/pytorch_model.bin b/embedders/transformers/korean_hubert_base/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..236676e6cba0bfc2fa433c0004e769b241a27165 --- /dev/null +++ b/embedders/transformers/korean_hubert_base/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3fa77495135b97e79aaf5353a2db9e0029b2e0496187dbbfbb4060d50365c43 +size 378356318 diff --git a/embedders/transformers/portuguese_hubert_base/config.json b/embedders/transformers/portuguese_hubert_base/config.json new file mode 100644 index 0000000000000000000000000000000000000000..c876d5034cc79c2eb9bd569d21c7866fa43701dc --- /dev/null +++ b/embedders/transformers/portuguese_hubert_base/config.json @@ -0,0 +1,72 @@ +{ + "activation_dropout": 0.1, + "apply_spec_augment": true, + "architectures": [ + "HubertModelWithFinalProj" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_pos_batch_norm": false, + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": true, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 12, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.48.3", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/embedders/transformers/portuguese_hubert_base/model.safetensors b/embedders/transformers/portuguese_hubert_base/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c3da7e7892ad2860bff78ae42712edf2335cfbbb --- /dev/null +++ b/embedders/transformers/portuguese_hubert_base/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321f39abff2f1d84b30b30fe08a639c75bff960fedb9569d0fcc1433f5f3def8 +size 378298264 diff --git a/embedders/transformers/portuguese_hubert_base/pytorch_model.bin b/embedders/transformers/portuguese_hubert_base/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..258dd540476a1f4f3a2b323d98866bcf7fa6e32f --- /dev/null +++ b/embedders/transformers/portuguese_hubert_base/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a7ef64fcb66ac9c3516af7f2bdc275ae75e8262d1939954b589899e89374841 +size 378356318 diff --git a/embedders/transformers/vietnamese_hubert_base/config.json b/embedders/transformers/vietnamese_hubert_base/config.json new file mode 100644 index 0000000000000000000000000000000000000000..c876d5034cc79c2eb9bd569d21c7866fa43701dc --- /dev/null +++ b/embedders/transformers/vietnamese_hubert_base/config.json @@ -0,0 +1,72 @@ +{ + "activation_dropout": 0.1, + "apply_spec_augment": true, + "architectures": [ + "HubertModelWithFinalProj" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "classifier_proj_size": 256, + "conv_bias": false, + "conv_dim": [ + 512, + 512, + 512, + 512, + 512, + 512, + 512 + ], + "conv_kernel": [ + 10, + 3, + 3, + 3, + 3, + 2, + 2 + ], + "conv_pos_batch_norm": false, + "conv_stride": [ + 5, + 2, + 2, + 2, + 2, + 2, + 2 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "do_stable_layer_norm": false, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_proj_layer_norm": true, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "model_type": "hubert", + "num_attention_heads": 12, + "num_conv_pos_embedding_groups": 16, + "num_conv_pos_embeddings": 128, + "num_feat_extract_layers": 7, + "num_hidden_layers": 12, + "pad_token_id": 0, + "torch_dtype": "float32", + "transformers_version": "4.48.3", + "use_weighted_layer_sum": false, + "vocab_size": 32 +} diff --git a/embedders/transformers/vietnamese_hubert_base/model.safetensors b/embedders/transformers/vietnamese_hubert_base/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..113454673db2d80a24e254412de00c94cb7f6d43 --- /dev/null +++ b/embedders/transformers/vietnamese_hubert_base/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19fc2fb6cb36185dceb0b41a9ea72dc1decf7ed9c3c30a9de295a1921398e287 +size 378298264 diff --git a/embedders/transformers/vietnamese_hubert_base/pytorch_model.bin b/embedders/transformers/vietnamese_hubert_base/pytorch_model.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a48afd9308b6d88070ebb12338efcb991b8e2ec --- /dev/null +++ b/embedders/transformers/vietnamese_hubert_base/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da3dcce3934d9e0ae522c307e3f94a35762c62923f72734771430ff9ab574b1c +size 378356318 diff --git a/ffmpeg/ffmpeg.exe b/ffmpeg/ffmpeg.exe new file mode 100644 index 0000000000000000000000000000000000000000..ddf3337846e74afb16a20a0f5405f10072199a06 --- /dev/null +++ b/ffmpeg/ffmpeg.exe @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6a4d917a444790f4c06ada640c1c0c95aecde2f8953ed8d0dfb19352500bfcd +size 52925440 diff --git a/ffmpeg/ffprobe.exe b/ffmpeg/ffprobe.exe new file mode 100644 index 0000000000000000000000000000000000000000..0cf5cc2a4e1e28d32820c0709996b386531fbde0 --- /dev/null +++ b/ffmpeg/ffprobe.exe @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2da5b980a9a14a808f423d181c4ed51c2b8af11b1366699f3f7eab0609926f8f +size 122135040 diff --git a/ico.png b/ico.png new file mode 100644 index 0000000000000000000000000000000000000000..580af75cf046842c56f42e0fb99be6155589a9a3 --- /dev/null +++ b/ico.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3580dfee1d9b4c8ed32870bb798a36d50e6586a0872a1da9bdbe4c3ca425b7f6 +size 3952719 diff --git a/json/custom_pretrained.json b/json/custom_pretrained.json new file mode 100644 index 0000000000000000000000000000000000000000..7c0afdc580116a3a72ebc93a43ca0feae0ba7929 --- /dev/null +++ b/json/custom_pretrained.json @@ -0,0 +1,121 @@ +{ + "RIN_E3": { + "40k": "RIN_E3.zip" + }, + "OV2Super": { + "32k": "f0Ov2Super32k.zip", + "40k": "f0Ov2Super40k.zip" + }, + "Itaila": { + "32k": "Italla_32k.zip" + }, + "SnowieRuPretrain": { + "40k": "Snowie_RuPretrain_EnP.zip", + "48k": "Snowie_RuPretrain_48k_V1.2.zip" + }, + "SnowieV3.1": { + "32k": "SnowieV3.1_32k.zip", + "40k": "SnowieV3.1_40k.zip", + "48k": "SnowieV3.1_48k.zip" + }, + "Snowie-X-RinE3": { + "40k": "Snowie-X-Rin-40k.zip" + }, + "Titan_Medium": { + "32k": "32k-TITAN-Medium.zip", + "40k": "40k-TITAN-Medium.zip", + "48k": "48k-TITAN-Medium.zip" + }, + "NanashiV1": { + "32k": "nanashi_v1.zip" + }, + "NanashiV1.5": { + "32k": "nanashi_v1.5.zip" + }, + "NanashiV1.7": { + "32k": "nanashi_v1.7.zip" + }, + "NanashiV2Base": { + "32k": "nanashi_v2_base.zip" + }, + "NanashiV2Finetune": { + "32k": "nanashi_v2_finetune.zip" + }, + "Nanashi_Anime_Normal": { + "32k": "nanashi_anime_384e.zip" + }, + "Nanashi_Anime_Resize": { + "32k": "nanashi_anime_resized.zip" + }, + "Rigel_Base": { + "32k": "Rigel_32k_3890220.zip" + }, + "Rigel_FineTuned": { + "32k": "Rigel_32k_fp32_2854856.zip" + }, + "RigelV1.5": { + "32k": "Rigel_Portuguese_50e.zip" + }, + "DMRV1": { + "32k": "DMR-V1.zip" + }, + "DMRV2": { + "32k": "DMR-V2.zip" + }, + "IMA": { + "32k": "IMA-TEST-V1.zip" + }, + "UKA": { + "32k": "UKA.zip" + }, + "SingerPretrain": { + "32k": "F0_SingerPretrain.zip" + }, + "GuideVocalPretrain": { + "48k": "GuideVocalPretrain.zip" + }, + "KLM_BeatzForge": { + "32k": "BeatzForge_V2_32k.zip", + "48k": "KLM_BeatzForge_48k.zip" + }, + "KLM_BeatMaster": { + "48k": "KLM_BeatMasterV1_48k.zip" + }, + "KLM4.0": { + "32k": "KLM4_32k.zip", + "40k": "KLM4_40k.zip", + "48k": "KLM4_48k.zip" + }, + "KLM4.1": { + "32k": "KLM41_32k.zip", + "48k": "KLM41_48k.zip" + }, + "KLM4.2": { + "32k": "KLM42_32k.zip", + "40k": "KLM42_T4_40k.zip" + }, + "KLM4.3_X1": { + "32k": "KLM43x1_32k.zip" + }, + "KLM4.3_X2": { + "32k": "KLM43x2_32k.zip" + }, + "KLM4.3_X3": { + "32k": "KLM43x3_32k.zip", + "40k": "KLM43x3_40k.zip", + "48k": "KLM43x3_48k.zip" + }, + "KLM4.3_X4": { + "32k": "KLM43x4_32k.zip", + "40k": "KLM43x4_40k.zip", + "48k": "KLM43x4_48k.zip" + }, + "KLM4.9_HFG": { + "32k": "KLM_HFG49_32k.zip", + "40k": "KLM_HFG49_40k.zip", + "48k": "KLM_HFG49_48k.zip" + }, + "Nezox": { + "32k": "Nezox_32k.zip" + } +} \ No newline at end of file diff --git a/json/model_data.json b/json/model_data.json new file mode 100644 index 0000000000000000000000000000000000000000..51c84dc6ac4b92ff648061423e0bab53943127be --- /dev/null +++ b/json/model_data.json @@ -0,0 +1,550 @@ +{ + "0ddfc0eb5792638ad5dc27850236c246": { + "compensate": 1.035, + "mdx_dim_f_set": 2048, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 6144, + "primary_stem": "Vocals" + }, + "26d308f91f3423a67dc69a6d12a8793d": { + "compensate": 1.035, + "mdx_dim_f_set": 2048, + "mdx_dim_t_set": 9, + "mdx_n_fft_scale_set": 8192, + "primary_stem": "Other" + }, + "2cdd429caac38f0194b133884160f2c6": { + "compensate": 1.045, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 7680, + "primary_stem": "Instrumental" + }, + "2f5501189a2f6db6349916fabe8c90de": { + "compensate": 1.035, + "mdx_dim_f_set": 2048, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 6144, + "primary_stem": "Vocals", + "is_karaoke": true + }, + "398580b6d5d973af3120df54cee6759d": { + "compensate": 1.75, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 7680, + "primary_stem": "Vocals" + }, + "488b3e6f8bd3717d9d7c428476be2d75": { + "compensate": 1.035, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 7680, + "primary_stem": "Instrumental" + }, + "4910e7827f335048bdac11fa967772f9": { + "compensate": 1.035, + "mdx_dim_f_set": 2048, + "mdx_dim_t_set": 7, + "mdx_n_fft_scale_set": 4096, + "primary_stem": "Drums" + }, + "53c4baf4d12c3e6c3831bb8f5b532b93": { + "compensate": 1.043, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 7680, + "primary_stem": "Vocals" + }, + "5d343409ef0df48c7d78cce9f0106781": { + "compensate": 1.075, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 7680, + "primary_stem": "Vocals" + }, + "5f6483271e1efb9bfb59e4a3e6d4d098": { + "compensate": 1.035, + "mdx_dim_f_set": 2048, + "mdx_dim_t_set": 9, + "mdx_n_fft_scale_set": 6144, + "primary_stem": "Vocals" + }, + "65ab5919372a128e4167f5e01a8fda85": { + "compensate": 1.035, + "mdx_dim_f_set": 2048, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 8192, + "primary_stem": "Other" + }, + "6703e39f36f18aa7855ee1047765621d": { + "compensate": 1.035, + "mdx_dim_f_set": 2048, + "mdx_dim_t_set": 9, + "mdx_n_fft_scale_set": 16384, + "primary_stem": "Bass" + }, + "6b31de20e84392859a3d09d43f089515": { + "compensate": 1.035, + "mdx_dim_f_set": 2048, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 6144, + "primary_stem": "Vocals" + }, + "867595e9de46f6ab699008295df62798": { + "compensate": 1.03, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 7680, + "primary_stem": "Vocals" + }, + "a3cd63058945e777505c01d2507daf37": { + "compensate": 1.03, + "mdx_dim_f_set": 2048, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 6144, + "primary_stem": "Vocals" + }, + "b33d9b3950b6cbf5fe90a32608924700": { + "compensate": 1.03, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 7680, + "primary_stem": "Vocals" + }, + "c3b29bdce8c4fa17ec609e16220330ab": { + "compensate": 1.035, + "mdx_dim_f_set": 2048, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 16384, + "primary_stem": "Bass" + }, + "ceed671467c1f64ebdfac8a2490d0d52": { + "compensate": 1.035, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 7680, + "primary_stem": "Instrumental" + }, + "d2a1376f310e4f7fa37fb9b5774eb701": { + "compensate": 1.035, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 7680, + "primary_stem": "Instrumental" + }, + "d7bff498db9324db933d913388cba6be": { + "compensate": 1.035, + "mdx_dim_f_set": 2048, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 6144, + "primary_stem": "Vocals" + }, + "d94058f8c7f1fae4164868ae8ae66b20": { + "compensate": 1.035, + "mdx_dim_f_set": 2048, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 6144, + "primary_stem": "Vocals" + }, + "dc41ede5961d50f277eb846db17f5319": { + "compensate": 1.035, + "mdx_dim_f_set": 2048, + "mdx_dim_t_set": 9, + "mdx_n_fft_scale_set": 4096, + "primary_stem": "Drums" + }, + "e5572e58abf111f80d8241d2e44e7fa4": { + "compensate": 1.028, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 7680, + "primary_stem": "Instrumental" + }, + "e7324c873b1f615c35c1967f912db92a": { + "compensate": 1.03, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 7680, + "primary_stem": "Vocals" + }, + "1c56ec0224f1d559c42fd6fd2a67b154": { + "compensate": 1.025, + "mdx_dim_f_set": 2048, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 5120, + "primary_stem": "Instrumental" + }, + "f2df6d6863d8f435436d8b561594ff49": { + "compensate": 1.035, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 7680, + "primary_stem": "Instrumental" + }, + "b06327a00d5e5fbc7d96e1781bbdb596": { + "compensate": 1.035, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 6144, + "primary_stem": "Instrumental" + }, + "94ff780b977d3ca07c7a343dab2e25dd": { + "compensate": 1.039, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 6144, + "primary_stem": "Instrumental" + }, + "73492b58195c3b52d34590d5474452f6": { + "compensate": 1.043, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 7680, + "primary_stem": "Vocals" + }, + "970b3f9492014d18fefeedfe4773cb42": { + "compensate": 1.009, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 7680, + "primary_stem": "Vocals" + }, + "1d64a6d2c30f709b8c9b4ce1366d96ee": { + "compensate": 1.065, + "mdx_dim_f_set": 2048, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 5120, + "primary_stem": "Instrumental", + "is_karaoke": true + }, + "203f2a3955221b64df85a41af87cf8f0": { + "compensate": 1.035, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 6144, + "primary_stem": "Instrumental" + }, + "291c2049608edb52648b96e27eb80e95": { + "compensate": 1.035, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 6144, + "primary_stem": "Instrumental" + }, + "ead8d05dab12ec571d67549b3aab03fc": { + "compensate": 1.035, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 6144, + "primary_stem": "Instrumental" + }, + "cc63408db3d80b4d85b0287d1d7c9632": { + "compensate": 1.033, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 6144, + "primary_stem": "Instrumental" + }, + "cd5b2989ad863f116c855db1dfe24e39": { + "compensate": 1.035, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 9, + "mdx_n_fft_scale_set": 6144, + "primary_stem": "Reverb" + }, + "55657dd70583b0fedfba5f67df11d711": { + "compensate": 1.022, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 6144, + "primary_stem": "Instrumental" + }, + "b6bccda408a436db8500083ef3491e8b": { + "compensate": 1.02, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 7680, + "primary_stem": "Instrumental" + }, + "8a88db95c7fb5dbe6a095ff2ffb428b1": { + "compensate": 1.026, + "mdx_dim_f_set": 2048, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 5120, + "primary_stem": "Instrumental" + }, + "b78da4afc6512f98e4756f5977f5c6b9": { + "compensate": 1.021, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 7680, + "primary_stem": "Instrumental" + }, + "77d07b2667ddf05b9e3175941b4454a0": { + "compensate": 1.021, + "mdx_dim_f_set": 3072, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 7680, + "primary_stem": "Vocals" + }, + "0f2a6bc5b49d87d64728ee40e23bceb1": { + "compensate": 1.019, + "mdx_dim_f_set": 2560, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 5120, + "primary_stem": "Instrumental" + }, + "cb790d0c913647ced70fc6b38f5bea1a": { + "compensate": 1.010, + "mdx_dim_f_set": 2560, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 5120, + "primary_stem": "Instrumental" + }, + "b02be2d198d4968a121030cf8950b492": { + "compensate": 1.020, + "mdx_dim_f_set": 2560, + "mdx_dim_t_set": 8, + "mdx_n_fft_scale_set": 5120, + "primary_stem": "No Crowd" + }, + "2154254ee89b2945b97a7efed6e88820": { + "config_yaml": "model_2_stem_061321.yaml" + }, + "063aadd735d58150722926dcbf5852a9": { + "config_yaml": "model_2_stem_061321.yaml" + }, + "c09f714d978b41d718facfe3427e6001": { + "config_yaml": "model_2_stem_061321.yaml" + }, + "fe96801369f6a148df2720f5ced88c19": { + "config_yaml": "model3.yaml" + }, + "02e8b226f85fb566e5db894b9931c640": { + "config_yaml": "model2.yaml" + }, + "e3de6d861635ab9c1d766149edd680d6": { + "config_yaml": "model1.yaml" + }, + "3f2936c554ab73ce2e396d54636bd373": { + "config_yaml": "modelB.yaml" + }, + "890d0f6f82d7574bca741a9e8bcb8168": { + "config_yaml": "modelB.yaml" + }, + "63a3cb8c37c474681049be4ad1ba8815": { + "config_yaml": "modelB.yaml" + }, + "a7fc5d719743c7fd6b61bd2b4d48b9f0": { + "config_yaml": "modelA.yaml" + }, + "3567f3dee6e77bf366fcb1c7b8bc3745": { + "config_yaml": "modelA.yaml" + }, + "a28f4d717bd0d34cd2ff7a3b0a3d065e": { + "config_yaml": "modelA.yaml" + }, + "c9971a18da20911822593dc81caa8be9": { + "config_yaml": "sndfx.yaml" + }, + "57d94d5ed705460d21c75a5ac829a605": { + "config_yaml": "sndfx.yaml" + }, + "e7a25f8764f25a52c1b96c4946e66ba2": { + "config_yaml": "sndfx.yaml" + }, + "104081d24e37217086ce5fde09147ee1": { + "config_yaml": "model_2_stem_061321.yaml" + }, + "1e6165b601539f38d0a9330f3facffeb": { + "config_yaml": "model_2_stem_061321.yaml" + }, + "fe0108464ce0d8271be5ab810891bd7c": { + "config_yaml": "model_2_stem_full_band.yaml" + }, + "e9b82ec90ee56c507a3a982f1555714c": { + "config_yaml": "model_2_stem_full_band_2.yaml" + }, + "99b6ceaae542265a3b6d657bf9fde79f": { + "config_yaml": "model_2_stem_full_band_8k.yaml" + }, + "116f6f9dabb907b53d847ed9f7a9475f": { + "config_yaml": "model_2_stem_full_band_8k.yaml" + }, + "53f707017bfcbb56f5e1bfac420d6732": { + "config_yaml": "model_bs_roformer_ep_317_sdr_12.9755.yaml", + "is_roformer": true + }, + "63e41acc264bf681a73aa9f7e5f606cc": { + "config_yaml": "model_mel_band_roformer_ep_3005_sdr_11.4360.yaml", + "is_roformer": true + }, + "e733736763234047587931fc35322fd9": { + "config_yaml": "model_bs_roformer_ep_937_sdr_10.5309.yaml", + "is_roformer": true + }, + "d7a256bee3e7c620f554bceaab2f68f6": { + "config_yaml": "config_melbandroformer_inst.yaml", + "is_roformer": true + }, + "365ccfa0e04b31ac2e24bbb935142a81": { + "config_yaml": "config_melbandroformer_inst.yaml", + "is_roformer": true + }, + "3c15abf122d8eccc4a0eb97bf84a3e58": { + "config_yaml": "config_melbandroformer_instvoc_duality.yaml", + "is_roformer": true + }, + "9fb197af219c5172ea38703a33aceb79": { + "config_yaml": "config_melbandroformer_instvoc_duality.yaml", + "is_roformer": true + }, + "d789065adfd747d6f585b27b495bcdae": { + "config_yaml": "model_bs_roformer_ep_368_sdr_12.9628.yaml", + "is_roformer": true + }, + "e4ca75912fcff3224a19058e55facfbf": { + "config_yaml": "config_vocals_mel_band_roformer_kim.yaml", + "is_roformer": true + }, + "951f8ef420a941a395a9919f5d55cce9": { + "config_yaml": "config_melbandroformer_inst_v2.yaml", + "is_roformer": true + }, + "0d0e6d143046b0eecc41a22e60224582": { + "vr_model_param": "3band_44100_mid", + "primary_stem": "Instrumental" + }, + "18b52f873021a0af556fb4ecd552bb8e": { + "vr_model_param": "2band_32000", + "primary_stem": "Instrumental" + }, + "1fc66027c82b499c7d8f55f79e64cadc": { + "vr_model_param": "2band_32000", + "primary_stem": "Instrumental" + }, + "2aa34fbc01f8e6d2bf509726481e7142": { + "vr_model_param": "4band_44100", + "primary_stem": "No Piano" + }, + "3e18f639b11abea7361db1a4a91c2559": { + "vr_model_param": "4band_44100", + "primary_stem": "Instrumental" + }, + "570b5f50054609a17741369a35007ddd": { + "vr_model_param": "4band_v3", + "primary_stem": "Instrumental" + }, + "5a6e24c1b530f2dab045a522ef89b751": { + "vr_model_param": "1band_sr44100_hl512", + "primary_stem": "Instrumental" + }, + "6b5916069a49be3fe29d4397ecfd73fa": { + "vr_model_param": "3band_44100_msb2", + "primary_stem": "Instrumental", + "is_karaoke": true + }, + "74b3bc5fa2b69f29baf7839b858bc679": { + "vr_model_param": "4band_44100", + "primary_stem": "Instrumental" + }, + "827213b316df36b52a1f3d04fec89369": { + "vr_model_param": "4band_44100", + "primary_stem": "Instrumental" + }, + "911d4048eee7223eca4ee0efb7d29256": { + "vr_model_param": "4band_44100", + "primary_stem": "Vocals" + }, + "941f3f7f0b0341f12087aacdfef644b1": { + "vr_model_param": "4band_v2", + "primary_stem": "Instrumental" + }, + "a02827cf69d75781a35c0e8a327f3195": { + "vr_model_param": "1band_sr33075_hl384", + "primary_stem": "Instrumental" + }, + "b165fbff113c959dba5303b74c6484bc": { + "vr_model_param": "3band_44100", + "primary_stem": "Instrumental" + }, + "b5f988cd3e891dca7253bf5f0f3427c7": { + "vr_model_param": "4band_44100", + "primary_stem": "Instrumental" + }, + "b99c35723bc35cb11ed14a4780006a80": { + "vr_model_param": "1band_sr44100_hl1024", + "primary_stem": "Instrumental" + }, + "ba02fd25b71d620eebbdb49e18e4c336": { + "vr_model_param": "3band_44100_mid", + "primary_stem": "Instrumental" + }, + "c4476ef424d8cba65f38d8d04e8514e2": { + "vr_model_param": "3band_44100_msb2", + "primary_stem": "Instrumental" + }, + "da2d37b8be2972e550a409bae08335aa": { + "vr_model_param": "4band_44100", + "primary_stem": "Vocals" + }, + "db57205d3133e39df8e050b435a78c80": { + "vr_model_param": "4band_44100", + "primary_stem": "Instrumental" + }, + "ea83b08e32ec2303456fe50659035f69": { + "vr_model_param": "4band_v3", + "primary_stem": "Instrumental" + }, + "f6ea8473ff86017b5ebd586ccacf156b": { + "vr_model_param": "4band_v2_sn", + "primary_stem": "Instrumental", + "is_karaoke": true + }, + "fd297a61eafc9d829033f8b987c39a3d": { + "vr_model_param": "1band_sr32000_hl512", + "primary_stem": "Instrumental" + }, + "0ec76fd9e65f81d8b4fbd13af4826ed8": { + "vr_model_param": "4band_v3", + "primary_stem": "No Woodwinds" + }, + "0fb9249ffe4ffc38d7b16243f394c0ff": { + "vr_model_param": "4band_v3", + "primary_stem": "No Reverb" + }, + "6857b2972e1754913aad0c9a1678c753": { + "vr_model_param": "4band_v3", + "primary_stem": "No Echo", + "nout": 48, + "nout_lstm": 128 + }, + "f200a145434efc7dcf0cd093f517ed52": { + "vr_model_param": "4band_v3", + "primary_stem": "No Echo", + "nout": 48, + "nout_lstm": 128 + }, + "44c55d8b5d2e3edea98c2b2bf93071c7": { + "vr_model_param": "4band_v3", + "primary_stem": "Noise", + "nout": 48, + "nout_lstm": 128 + }, + "51ea8c43a6928ed3c10ef5cb2707d57b": { + "vr_model_param": "1band_sr44100_hl1024", + "primary_stem": "Noise", + "nout": 16, + "nout_lstm": 128 + }, + "944950a9c5963a5eb70b445d67b7068a": { + "vr_model_param": "4band_v3_sn", + "primary_stem": "Vocals", + "nout": 64, + "nout_lstm": 128, + "is_karaoke": false, + "is_bv_model": true, + "is_bv_model_rebalanced": 0.9 + } +} diff --git a/json/uvr_models.json b/json/uvr_models.json new file mode 100644 index 0000000000000000000000000000000000000000..64e1bbd2c034acf1ea9ba2b4f75fff1b069b36dd --- /dev/null +++ b/json/uvr_models.json @@ -0,0 +1,84 @@ +{ + "mdx_download_list": { + "MDX-Net Model: UVR-MDX-NET Inst HQ 1": "UVR-MDX-NET-Inst_HQ_1.onnx", + "MDX-Net Model: UVR-MDX-NET Inst HQ 2": "UVR-MDX-NET-Inst_HQ_2.onnx", + "MDX-Net Model: UVR-MDX-NET Inst HQ 3": "UVR-MDX-NET-Inst_HQ_3.onnx", + "MDX-Net Model: UVR-MDX-NET Inst HQ 4": "UVR-MDX-NET-Inst_HQ_4.onnx", + "MDX-Net Model: UVR-MDX-NET Inst HQ 5": "UVR-MDX-NET-Inst_HQ_5.onnx", + "MDX-Net Model: UVR-MDX-NET Main": "UVR_MDXNET_Main.onnx", + "MDX-Net Model: UVR-MDX-NET Inst Main": "UVR-MDX-NET-Inst_Main.onnx", + "MDX-Net Model: UVR-MDX-NET 1": "UVR_MDXNET_1_9703.onnx", + "MDX-Net Model: UVR-MDX-NET 2": "UVR_MDXNET_2_9682.onnx", + "MDX-Net Model: UVR-MDX-NET 3": "UVR_MDXNET_3_9662.onnx", + "MDX-Net Model: UVR-MDX-NET Inst 1": "UVR-MDX-NET-Inst_1.onnx", + "MDX-Net Model: UVR-MDX-NET Inst 2": "UVR-MDX-NET-Inst_2.onnx", + "MDX-Net Model: UVR-MDX-NET Inst 3": "UVR-MDX-NET-Inst_3.onnx", + "MDX-Net Model: UVR-MDX-NET Karaoke": "UVR_MDXNET_KARA.onnx", + "MDX-Net Model: UVR-MDX-NET Karaoke 2": "UVR_MDXNET_KARA_2.onnx", + "MDX-Net Model: UVR_MDXNET_9482": "UVR_MDXNET_9482.onnx", + "MDX-Net Model: UVR-MDX-NET Voc FT": "UVR-MDX-NET-Voc_FT.onnx", + "MDX-Net Model: Kim Vocal 1": "Kim_Vocal_1.onnx", + "MDX-Net Model: Kim Vocal 2": "Kim_Vocal_2.onnx", + "MDX-Net Model: Kim Inst": "Kim_Inst.onnx", + "MDX-Net Model: Reverb HQ By FoxJoy": "Reverb_HQ_By_FoxJoy.onnx", + "MDX-Net Model: UVR-MDX-NET Crowd HQ 1 By Aufr33": "UVR-MDX-NET_Crowd_HQ_1.onnx" + }, + + "demucs_download_list":{ + "Demucs v4: htdemucs_ft":{ + "f7e0c4bc-ba3fe64a.th":"f7e0c4bc-ba3fe64a.th", + "d12395a8-e57c48e6.th":"d12395a8-e57c48e6.th", + "92cfc3b6-ef3bcb9c.th":"92cfc3b6-ef3bcb9c.th", + "04573f0d-f3cf25b2.th":"04573f0d-f3cf25b2.th", + "htdemucs_ft.yaml": "htdemucs_ft.yaml" + }, + "Demucs v4: htdemucs":{ + "955717e8-8726e21a.th": "955717e8-8726e21a.th", + "htdemucs.yaml": "htdemucs.yaml" + }, + "Demucs v4: hdemucs_mmi":{ + "75fc33f5-1941ce65.th": "75fc33f5-1941ce65.th", + "hdemucs_mmi.yaml": "hdemucs_mmi.yaml" + }, + "Demucs v4: htdemucs_6s":{ + "5c90dfd2-34c22ccb.th": "5c90dfd2-34c22ccb.th", + "htdemucs_6s.yaml": "htdemucs_6s.yaml" + } + }, + + "mdx_download_vip_list": { + "MDX-Net Model VIP: UVR-MDX-NET_Main_340": "UVR-MDX-NET_Main_340.onnx", + "MDX-Net Model VIP: UVR-MDX-NET_Main_390": "UVR-MDX-NET_Main_390.onnx", + "MDX-Net Model VIP: UVR-MDX-NET_Main_406": "UVR-MDX-NET_Main_406.onnx", + "MDX-Net Model VIP: UVR-MDX-NET_Main_427": "UVR-MDX-NET_Main_427.onnx", + "MDX-Net Model VIP: UVR-MDX-NET_Main_438": "UVR-MDX-NET_Main_438.onnx", + "MDX-Net Model VIP: UVR-MDX-NET_Inst_82_beta": "UVR-MDX-NET_Inst_82_beta.onnx", + "MDX-Net Model VIP: UVR-MDX-NET_Inst_90_beta": "UVR-MDX-NET_Inst_90_beta.onnx", + "MDX-Net Model VIP: UVR-MDX-NET_Inst_187_beta": "UVR-MDX-NET_Inst_187_beta.onnx", + "MDX-Net Model VIP: UVR-MDX-NET-Inst_full_292": "UVR-MDX-NET-Inst_full_292.onnx" + }, + + "vr_download_list": { + "VR Arch Single Model v5: 1_HP-UVR": "1_HP-UVR.pth", + "VR Arch Single Model v5: 2_HP-UVR": "2_HP-UVR.pth", + "VR Arch Single Model v5: 3_HP-Vocal-UVR": "3_HP-Vocal-UVR.pth", + "VR Arch Single Model v5: 4_HP-Vocal-UVR": "4_HP-Vocal-UVR.pth", + "VR Arch Single Model v5: 5_HP-Karaoke-UVR": "5_HP-Karaoke-UVR.pth", + "VR Arch Single Model v5: 6_HP-Karaoke-UVR": "6_HP-Karaoke-UVR.pth", + "VR Arch Single Model v5: 7_HP2-UVR": "7_HP2-UVR.pth", + "VR Arch Single Model v5: 8_HP2-UVR": "8_HP2-UVR.pth", + "VR Arch Single Model v5: 9_HP2-UVR": "9_HP2-UVR.pth", + "VR Arch Single Model v5: 10_SP-UVR-2B-32000-1": "10_SP-UVR-2B-32000-1.pth", + "VR Arch Single Model v5: 11_SP-UVR-2B-32000-2": "11_SP-UVR-2B-32000-2.pth", + "VR Arch Single Model v5: 12_SP-UVR-3B-44100": "12_SP-UVR-3B-44100.pth", + "VR Arch Single Model v5: 13_SP-UVR-4B-44100-1": "13_SP-UVR-4B-44100-1.pth", + "VR Arch Single Model v5: 14_SP-UVR-4B-44100-2": "14_SP-UVR-4B-44100-2.pth", + "VR Arch Single Model v5: 15_SP-UVR-MID-44100-1": "15_SP-UVR-MID-44100-1.pth", + "VR Arch Single Model v5: 16_SP-UVR-MID-44100-2": "16_SP-UVR-MID-44100-2.pth", + "VR Arch Single Model v5: UVR-De-Echo-Aggressive by FoxJoy": "UVR-De-Echo-Aggressive.pth", + "VR Arch Single Model v5: UVR-De-Echo-Normal by FoxJoy": "UVR-De-Echo-Normal.pth", + "VR Arch Single Model v5: UVR-DeEcho-DeReverb by FoxJoy": "UVR-DeEcho-DeReverb.pth", + "VR Arch Single Model v5: UVR-DeNoise-Lite by FoxJoy": "UVR-DeNoise-Lite.pth", + "VR Arch Single Model v5: UVR-DeNoise by FoxJoy": "UVR-DeNoise.pth" + } +} \ No newline at end of file diff --git a/predictors/World/world64.dll b/predictors/World/world64.dll new file mode 100644 index 0000000000000000000000000000000000000000..df033197619d3adc45804438de16c6229c5f510a Binary files /dev/null and b/predictors/World/world64.dll differ diff --git a/predictors/World/world86.dll b/predictors/World/world86.dll new file mode 100644 index 0000000000000000000000000000000000000000..dd0e21de0a54292d0f8e8bbba70cadbfdd40cca0 Binary files /dev/null and b/predictors/World/world86.dll differ diff --git a/predictors/World/world_android64.so b/predictors/World/world_android64.so new file mode 100644 index 0000000000000000000000000000000000000000..38a82b456829f53057f68ac542570e8d8a17a23c Binary files /dev/null and b/predictors/World/world_android64.so differ diff --git a/predictors/World/world_android86.so b/predictors/World/world_android86.so new file mode 100644 index 0000000000000000000000000000000000000000..e7f0448dcb95a996d62407603460c8d5ab2e7212 Binary files /dev/null and b/predictors/World/world_android86.so differ diff --git a/predictors/World/world_arm64.so b/predictors/World/world_arm64.so new file mode 100644 index 0000000000000000000000000000000000000000..932c54fcb3317ecf63cc3f55d49262c552a458a3 Binary files /dev/null and b/predictors/World/world_arm64.so differ diff --git a/predictors/World/world_arm_eabi.so b/predictors/World/world_arm_eabi.so new file mode 100644 index 0000000000000000000000000000000000000000..bfc99187c1e950f4c01ebf05999efb0f0c1ace29 Binary files /dev/null and b/predictors/World/world_arm_eabi.so differ diff --git a/predictors/World/world_linux.so b/predictors/World/world_linux.so new file mode 100644 index 0000000000000000000000000000000000000000..8947e17d7572d4e2bd9d741e21218f2f92a36be1 Binary files /dev/null and b/predictors/World/world_linux.so differ diff --git a/predictors/World/world_mac.dylib b/predictors/World/world_mac.dylib new file mode 100644 index 0000000000000000000000000000000000000000..43b9daaa856be6a958656bdc4f22bf171c30ed8c Binary files /dev/null and b/predictors/World/world_mac.dylib differ diff --git a/predictors/crepe_full.onnx b/predictors/crepe_full.onnx new file mode 100644 index 0000000000000000000000000000000000000000..935aab9b5b8336d9eb88b4614a4202826044ed1f --- /dev/null +++ b/predictors/crepe_full.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:119845c72c702e052e5262430f9d120bce46176689aa226c39d09dea5cc3a610 +size 88984790 diff --git a/predictors/crepe_full.pth b/predictors/crepe_full.pth new file mode 100644 index 0000000000000000000000000000000000000000..5767e7588ea2c31446b76062aadcfd17864fdd5d --- /dev/null +++ b/predictors/crepe_full.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:133225604dedd2e4005f8bbd1bd0a2ec073ba8b7a6cd31ff6d5edbbfa3539986 +size 88991291 diff --git a/predictors/crepe_large.onnx b/predictors/crepe_large.onnx new file mode 100644 index 0000000000000000000000000000000000000000..e2e86a1c9dcfc2ff51b59af7cbcc2db63b66a75a --- /dev/null +++ b/predictors/crepe_large.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f1a5245982dad1a4a357278861ad1ea0d0aed6f04888dcec92df9b8c873a790 +size 51012147 diff --git a/predictors/crepe_large.pth b/predictors/crepe_large.pth new file mode 100644 index 0000000000000000000000000000000000000000..0e558f98db754a22a7f1542bd7765dd384a2b555 --- /dev/null +++ b/predictors/crepe_large.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d94363dd631abffa79bac02c6072828b3ef7bc78c52b83730a68d1e5d9d2ce20 +size 51013392 diff --git a/predictors/crepe_medium.onnx b/predictors/crepe_medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..e78b605d5d96c88ccf275432e261fc7f35c67431 --- /dev/null +++ b/predictors/crepe_medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bd7cd61bfd07596c7861e580ca04ef7170407994956d4c554ffd4863fb43ae3 +size 23525293 diff --git a/predictors/crepe_medium.pth b/predictors/crepe_medium.pth new file mode 100644 index 0000000000000000000000000000000000000000..5615909af55f2dc5c68ea2e0aa0c684284c19853 --- /dev/null +++ b/predictors/crepe_medium.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:094c3e72fed320e22281b58912945be8f74cd910f0b77352ebbbfcbcf8cbbacb +size 23526586 diff --git a/predictors/crepe_small.onnx b/predictors/crepe_small.onnx new file mode 100644 index 0000000000000000000000000000000000000000..74d6cc7fc855e92eeabb93a8141de7fc6b3dd813 --- /dev/null +++ b/predictors/crepe_small.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd119f6f5f608d9342a1c6f81e4653f21dbcde440a96d474ecbf6f27c6253466 +size 6524192 diff --git a/predictors/crepe_small.pth b/predictors/crepe_small.pth new file mode 100644 index 0000000000000000000000000000000000000000..7be16b1b06d23f1ae8fa4e4a54f39d5ef7c06fbf --- /dev/null +++ b/predictors/crepe_small.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b785e0300a5eefdf56f31788142b6c9432d7417e5a2c64f4375f979e7ceaf53 +size 6525456 diff --git a/predictors/crepe_tiny.onnx b/predictors/crepe_tiny.onnx new file mode 100644 index 0000000000000000000000000000000000000000..882bea1d0bb51d4e095d6d900452872501345ac2 --- /dev/null +++ b/predictors/crepe_tiny.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91fc2a0fd10f965dbf7775995daf50e99273caedd7efd00001f23be649da1bc3 +size 1955762 diff --git a/predictors/crepe_tiny.pth b/predictors/crepe_tiny.pth new file mode 100644 index 0000000000000000000000000000000000000000..79d10d896a956c54dee45257cfe6bf87425bbdf5 --- /dev/null +++ b/predictors/crepe_tiny.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4993eea36ed1a0ad9ac549c740dae5265b049ce72004f00c2f59e01c0be8432 +size 1962363 diff --git a/predictors/ddsp_200k.onnx b/predictors/ddsp_200k.onnx new file mode 100644 index 0000000000000000000000000000000000000000..81d46a3cd163ca182ca48882ab3fc2fb1f4c1f64 --- /dev/null +++ b/predictors/ddsp_200k.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ced15a5c0bcaba675ce3412e09b4ef3a9f6f7642ae655511e29ac08ce0b52849 +size 43343792 diff --git a/predictors/ddsp_200k.pt b/predictors/ddsp_200k.pt new file mode 100644 index 0000000000000000000000000000000000000000..0ee56f5b0321c8b574d5a4cc69eb0e484522dab9 --- /dev/null +++ b/predictors/ddsp_200k.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8544427eebbf2baef6213cc9a05057e46961617a8e5bd96975a0d42da6a09059 +size 43362881 diff --git a/predictors/djcm.onnx b/predictors/djcm.onnx new file mode 100644 index 0000000000000000000000000000000000000000..29957dcb8927a3b20d6bc3bb73e85414d3be4783 --- /dev/null +++ b/predictors/djcm.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60de141a7c1fee0492079c93830d612458c9eee56048779869ce9c0a53ea920a +size 88847983 diff --git a/predictors/djcm.pt b/predictors/djcm.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b562f42c4f4cfe4c7df55ed868573f16a32cb47 --- /dev/null +++ b/predictors/djcm.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d088fbca601d7353f3cc4e780d999bbe1c3c62c1a1c0a8e7a0a2695dcceb4bd +size 88890686 diff --git a/predictors/fcn.onnx b/predictors/fcn.onnx new file mode 100644 index 0000000000000000000000000000000000000000..4921ba4d66d1f151ff9a2f0153004d18ef7a608b --- /dev/null +++ b/predictors/fcn.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e73f196408941df6d8ef0df859acf9f7435388d9a34ce050e656976fafa92527 +size 35745871 diff --git a/predictors/fcn.pt b/predictors/fcn.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ba33df292339752f446bddab8719301348e1bbd --- /dev/null +++ b/predictors/fcn.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f5c249b8245d46d4363e49d5f036226c0abc2432ace65fe9afa7c5b2ad5e93b +size 35745070 diff --git a/predictors/fcpe.onnx b/predictors/fcpe.onnx new file mode 100644 index 0000000000000000000000000000000000000000..9b6e658cb84235db6b2fca833e06b9e5fef7a058 --- /dev/null +++ b/predictors/fcpe.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5df9772e08965ade3b9d568caac208ff0d9260b5934349b711c09e5c29240350 +size 43343792 diff --git a/predictors/fcpe.pt b/predictors/fcpe.pt new file mode 100644 index 0000000000000000000000000000000000000000..08c6c8e893a5785ff6ae018cb2037f4ef5700721 --- /dev/null +++ b/predictors/fcpe.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9aeaeb673436eeda50ceafd632aa681aa63417e52eae4207503d180c9b10015 +size 43363260 diff --git a/predictors/fcpe_legacy.onnx b/predictors/fcpe_legacy.onnx new file mode 100644 index 0000000000000000000000000000000000000000..d1571ed3c1a11e2988a2cddc2ac2063045af1228 --- /dev/null +++ b/predictors/fcpe_legacy.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6356b42b38848bd218b2bef6412a340634d6db1209f85864f4fe46920f113cf5 +size 69197120 diff --git a/predictors/fcpe_legacy.pt b/predictors/fcpe_legacy.pt new file mode 100644 index 0000000000000000000000000000000000000000..a35dba1e7ece5897aeceff4dea92afaa60ca8244 --- /dev/null +++ b/predictors/fcpe_legacy.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3a8dd2dbd51baf19ed295006f2ac25dba6dd60adc7ec578ae5fbd94970951da +size 69005189 diff --git a/predictors/pesto.onnx b/predictors/pesto.onnx new file mode 100644 index 0000000000000000000000000000000000000000..382e049840d53b3dd247207c776e93ecd82e5fee --- /dev/null +++ b/predictors/pesto.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3e41f50909eaa41064f8b87e1a6381372a3befba895c70c840f2147819c6f77 +size 8777048 diff --git a/predictors/pesto.pt b/predictors/pesto.pt new file mode 100644 index 0000000000000000000000000000000000000000..c05f87c47fb17e8f27535745d4444b59255cec88 --- /dev/null +++ b/predictors/pesto.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb06a8dde663469045acd839015cefa0d8968cabb617e611883e7e52d20a9386 +size 530848 diff --git a/predictors/rmvpe.onnx b/predictors/rmvpe.onnx new file mode 100644 index 0000000000000000000000000000000000000000..797d6e39af999a673f89416496fa55161bbf30cd --- /dev/null +++ b/predictors/rmvpe.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0b5d71c5ae88e78efc6aebd8bf3f734de983f5bc93e39bcb158d88cd4c59f32 +size 180938246 diff --git a/predictors/rmvpe.pt b/predictors/rmvpe.pt new file mode 100644 index 0000000000000000000000000000000000000000..6362f060846875c3b5d7012adea5f97e47305e7e --- /dev/null +++ b/predictors/rmvpe.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d62215f4306e3ca278246188607209f09af3dc77ed4232efdd069798c4ec193 +size 181184272 diff --git a/predictors/swift.onnx b/predictors/swift.onnx new file mode 100644 index 0000000000000000000000000000000000000000..d80de76695607102f603c3f4d3d5df44dfaeb0de --- /dev/null +++ b/predictors/swift.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e2390db8379cd9e1e2b22828e55b45b57c8559e4c8335678c717dc245c18176 +size 397987 diff --git a/pretrained_custom/32k-TITAN-Medium.zip b/pretrained_custom/32k-TITAN-Medium.zip new file mode 100644 index 0000000000000000000000000000000000000000..d5fd31dbbae61cf5928158b1868d4ebae146e78c --- /dev/null +++ b/pretrained_custom/32k-TITAN-Medium.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:666a567a7ceca725b9095070e1582c15c14cd28cb4ec6be9ed7686ae663fd749 +size 1201484506 diff --git a/pretrained_custom/40k-TITAN-Medium.zip b/pretrained_custom/40k-TITAN-Medium.zip new file mode 100644 index 0000000000000000000000000000000000000000..9e2667156dbf7f0355d0182b7680ff0d7af352e1 --- /dev/null +++ b/pretrained_custom/40k-TITAN-Medium.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e211c56bbc4fd3c878c1f4140a26560e5a1bb214e94c72ade8b669c85e66fb9e +size 1197518690 diff --git a/pretrained_custom/48k-TITAN-Medium.zip b/pretrained_custom/48k-TITAN-Medium.zip new file mode 100644 index 0000000000000000000000000000000000000000..31d3d012598d746194a7c20df42cba6a789a0c74 --- /dev/null +++ b/pretrained_custom/48k-TITAN-Medium.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f3dc13666a0bfc58f25403ce3c59d1a91ea2cf4d0405f831c81786582ff5bdb +size 1209770373 diff --git a/pretrained_custom/BeatzForge_V2_32k.zip b/pretrained_custom/BeatzForge_V2_32k.zip new file mode 100644 index 0000000000000000000000000000000000000000..1beb47357239d9d0a98f1c4c758f980ed64fb9f4 --- /dev/null +++ b/pretrained_custom/BeatzForge_V2_32k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e30be21efc30826e78577e6ff2b9e962821d5c36ae3e73a5a03dd079b8131588 +size 1200246638 diff --git a/pretrained_custom/DMR-V1.zip b/pretrained_custom/DMR-V1.zip new file mode 100644 index 0000000000000000000000000000000000000000..8918ebdd0d10d3dc8565d413c453972a079d1b5e --- /dev/null +++ b/pretrained_custom/DMR-V1.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:155b9aa018daac0d0216f287c30a404b40dc900297a2c4aaf57bd5818c153bfc +size 1201855208 diff --git a/pretrained_custom/F0_SingerPretrain.zip b/pretrained_custom/F0_SingerPretrain.zip new file mode 100644 index 0000000000000000000000000000000000000000..fdee96e966fe0e814e1e4debd693c3d63b504378 --- /dev/null +++ b/pretrained_custom/F0_SingerPretrain.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47ab50e390a5b4315ee196a3d0fd8b16af2474fd8d054e4acf1f2a8e30977844 +size 1201389513 diff --git a/pretrained_custom/GuideVocalPretrain.zip b/pretrained_custom/GuideVocalPretrain.zip new file mode 100644 index 0000000000000000000000000000000000000000..9c1ddee682dd81886dd0315069aa0fa9e7c0b78e --- /dev/null +++ b/pretrained_custom/GuideVocalPretrain.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaf7eda3545e8fd9ddd95be38ea658e0b00d35888767ca54e0855d6b0dfbbbac +size 1212429694 diff --git a/pretrained_custom/IMA-TEST-V1.zip b/pretrained_custom/IMA-TEST-V1.zip new file mode 100644 index 0000000000000000000000000000000000000000..ad9a95a90d58830884f95355c0c5f96e7b1388d7 --- /dev/null +++ b/pretrained_custom/IMA-TEST-V1.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96b499d25d502ec017b93f449da79a7ae8aed17e42f015ac6e079b981d8b2f9d +size 1200984101 diff --git a/pretrained_custom/Italla_32k.zip b/pretrained_custom/Italla_32k.zip new file mode 100644 index 0000000000000000000000000000000000000000..2eb6aa923211965216b27a1dd435a0e91e5d282c --- /dev/null +++ b/pretrained_custom/Italla_32k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac3786c932a1a60cc153483538b448139c0f70382c39b88bdd05d292d65162fd +size 1201838863 diff --git a/pretrained_custom/KLM41_32k.zip b/pretrained_custom/KLM41_32k.zip new file mode 100644 index 0000000000000000000000000000000000000000..dc81bd714bf75d1b2c8b1d8662f3e0751dfbd476 --- /dev/null +++ b/pretrained_custom/KLM41_32k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a90d9805036c96d92e486f1ce663c2e09705cd09820b47422c25bd7e00abf294 +size 1201230891 diff --git a/pretrained_custom/KLM41_48k.zip b/pretrained_custom/KLM41_48k.zip new file mode 100644 index 0000000000000000000000000000000000000000..398f15256234cdf7668f08ef815814dbd966c3fa --- /dev/null +++ b/pretrained_custom/KLM41_48k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b2abd813275e73ae246df2fe47273535c3a068ef3ee2f98b297fd2fb764bd5 +size 1210599580 diff --git a/pretrained_custom/KLM42_32k.zip b/pretrained_custom/KLM42_32k.zip new file mode 100644 index 0000000000000000000000000000000000000000..e239cdef528aaadeefb34026159148fde68718a3 --- /dev/null +++ b/pretrained_custom/KLM42_32k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c787abe7457269900136944cd41edc9be4fa06c79ea75a760f96f10555ca275b +size 1201656197 diff --git a/pretrained_custom/KLM42_T4_40k.zip b/pretrained_custom/KLM42_T4_40k.zip new file mode 100644 index 0000000000000000000000000000000000000000..87dcf4013036beed6013a3170ecf9882c2959ed9 --- /dev/null +++ b/pretrained_custom/KLM42_T4_40k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4923a51bee60b1221448d4694add42f169dd4c2b2465de788432630b2856227 +size 1199331631 diff --git a/pretrained_custom/KLM43x1_32k.zip b/pretrained_custom/KLM43x1_32k.zip new file mode 100644 index 0000000000000000000000000000000000000000..10ba5bbcd091afbf34f044e843556b6a51d3bb22 --- /dev/null +++ b/pretrained_custom/KLM43x1_32k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9201d8ae5bffb182c47c10606e188b5ba48773cb69334994e68912c7a8df1f0 +size 1204882403 diff --git a/pretrained_custom/KLM43x2_32k.zip b/pretrained_custom/KLM43x2_32k.zip new file mode 100644 index 0000000000000000000000000000000000000000..6096aee9895f05af662964e0e8b45982c281aeca --- /dev/null +++ b/pretrained_custom/KLM43x2_32k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82b1249b382abd83209fc5d1662f93828c4cfbf90dc0187bbea5853999cddbdf +size 1205272919 diff --git a/pretrained_custom/KLM43x3_32k.zip b/pretrained_custom/KLM43x3_32k.zip new file mode 100644 index 0000000000000000000000000000000000000000..d30ba91849d60eb73a06eb061b0ea45f43d3735d --- /dev/null +++ b/pretrained_custom/KLM43x3_32k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abb1142ed4fc87e4c76ce4b41ea13829135ab4f1273e73890badc72e2527508a +size 1202572304 diff --git a/pretrained_custom/KLM43x3_40k.zip b/pretrained_custom/KLM43x3_40k.zip new file mode 100644 index 0000000000000000000000000000000000000000..5b62c8d4786e67363aa3886552a8f5f87a5089b2 --- /dev/null +++ b/pretrained_custom/KLM43x3_40k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4bb199de5b051e4226d641261586383c7ffbd99827275fae58e6853d0bbe65a +size 1197465597 diff --git a/pretrained_custom/KLM43x3_48k.zip b/pretrained_custom/KLM43x3_48k.zip new file mode 100644 index 0000000000000000000000000000000000000000..ba3c1ca79dee1aaaaac9ba617578de42845d3d2e --- /dev/null +++ b/pretrained_custom/KLM43x3_48k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f712b192e622713a5c8e55912ccc7cd26c7a2a1a9c2ced92f86b80c9d249f36c +size 1211228426 diff --git a/pretrained_custom/KLM43x4_32k.zip b/pretrained_custom/KLM43x4_32k.zip new file mode 100644 index 0000000000000000000000000000000000000000..d0dc3622079d16dba850925c93ce3def8158d32f --- /dev/null +++ b/pretrained_custom/KLM43x4_32k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be60f3177367af2af3821272db42bd7371b33a344b5d9d4203c1dbfbdb11f8df +size 1203638754 diff --git a/pretrained_custom/KLM43x4_40k.zip b/pretrained_custom/KLM43x4_40k.zip new file mode 100644 index 0000000000000000000000000000000000000000..12f242c7e890af3c488227d9b121e97d7afc2646 --- /dev/null +++ b/pretrained_custom/KLM43x4_40k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7af1e1022d0dacca8f2d0ab0b717ec6c4a9ea3c2c54bb48dd622ee498d21ea36 +size 1198937435 diff --git a/pretrained_custom/KLM43x4_48k.zip b/pretrained_custom/KLM43x4_48k.zip new file mode 100644 index 0000000000000000000000000000000000000000..99c71d37b44b5ad57d68a71f5f3658383bc1dce9 --- /dev/null +++ b/pretrained_custom/KLM43x4_48k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f9124f9a607324b55130033d7b5c8363090899a83b9014bd5ca432c46017239 +size 1211919378 diff --git a/pretrained_custom/KLM4_32k.zip b/pretrained_custom/KLM4_32k.zip new file mode 100644 index 0000000000000000000000000000000000000000..57a5bf07b1330b66d0ded9a6218da1acb4a14501 --- /dev/null +++ b/pretrained_custom/KLM4_32k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af1dd65dd470b52efe12f0bab4cf9c83d0b66bb67d02f3a89f92edb76f8ba5e9 +size 1198938845 diff --git a/pretrained_custom/KLM4_40k.zip b/pretrained_custom/KLM4_40k.zip new file mode 100644 index 0000000000000000000000000000000000000000..75286287bba4e197cb70a862ffc95a52092c7d41 --- /dev/null +++ b/pretrained_custom/KLM4_40k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1bf40bb3fc70b8265d842b042d18e14ab45d50d13fb4afc94845a3b73bd7997 +size 1194988924 diff --git a/pretrained_custom/KLM4_48k.zip b/pretrained_custom/KLM4_48k.zip new file mode 100644 index 0000000000000000000000000000000000000000..37a62560a8b60f843b1a8e1c85dcf413a6228e4a --- /dev/null +++ b/pretrained_custom/KLM4_48k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce60da68030290ef0e4fa5a461859998474912134e77ddd3577c14e234dbfc39 +size 1208871900 diff --git a/pretrained_custom/KLM_BeatMasterV1_48k.zip b/pretrained_custom/KLM_BeatMasterV1_48k.zip new file mode 100644 index 0000000000000000000000000000000000000000..caa3720b59236990acfcf5cb149ee6f18a245d32 --- /dev/null +++ b/pretrained_custom/KLM_BeatMasterV1_48k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36307c93eb5a81bc03f79747471e2ad9f05cfa5db6a465c4233c283f1877f2e8 +size 1209979129 diff --git a/pretrained_custom/KLM_BeatzForge_48k.zip b/pretrained_custom/KLM_BeatzForge_48k.zip new file mode 100644 index 0000000000000000000000000000000000000000..f74ce4e9152e08d02a85ce504560fc92b81492b5 --- /dev/null +++ b/pretrained_custom/KLM_BeatzForge_48k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91b85f9a07fc8fc0492ec1504a1913b3694017ab33ed74fa54ce29af64975584 +size 1209590139 diff --git a/pretrained_custom/KLM_HFG49_32k.zip b/pretrained_custom/KLM_HFG49_32k.zip new file mode 100644 index 0000000000000000000000000000000000000000..ce94cf1394be6dc2ebdef7205b3f26c72f528469 --- /dev/null +++ b/pretrained_custom/KLM_HFG49_32k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd88d5ca005956b9bd0ef11ecbcc0173507dfbb555d134718b9047427dd4723f +size 1201590610 diff --git a/pretrained_custom/KLM_HFG49_40k.zip b/pretrained_custom/KLM_HFG49_40k.zip new file mode 100644 index 0000000000000000000000000000000000000000..f51599195c1cfeb030790bd10f5ebcad6f652dea --- /dev/null +++ b/pretrained_custom/KLM_HFG49_40k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb58d86b205281bfb2720d94b221fb5454c5ed6facab77ef073452bf9502bad6 +size 1197705957 diff --git a/pretrained_custom/KLM_HFG49_48k.zip b/pretrained_custom/KLM_HFG49_48k.zip new file mode 100644 index 0000000000000000000000000000000000000000..eb70ddc765fb707f386c703c323055a803b02a91 --- /dev/null +++ b/pretrained_custom/KLM_HFG49_48k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6712faac3c554f75b37111700ebf19b9b51f7f2be661942e8056c7c0793d5c52 +size 1210769328 diff --git a/pretrained_custom/Nezox_32k.zip b/pretrained_custom/Nezox_32k.zip new file mode 100644 index 0000000000000000000000000000000000000000..e1ea4009dfb651d8c247d01d1087ab179c50e289 --- /dev/null +++ b/pretrained_custom/Nezox_32k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:244d277b84f5c5cdb0899d473985e6e093e3e6a9e811215a4d4d98cee2366203 +size 1202602376 diff --git a/pretrained_custom/RIN_E3.zip b/pretrained_custom/RIN_E3.zip new file mode 100644 index 0000000000000000000000000000000000000000..703865b616739e0d662b03fa07b5eb96c80ca36a --- /dev/null +++ b/pretrained_custom/RIN_E3.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25f1946baae51176ba71eb97f3ed7c7d213467e1f97fb6565c7b1397fea09c52 +size 1198406271 diff --git a/pretrained_custom/Rigel_32k_3890220.zip b/pretrained_custom/Rigel_32k_3890220.zip new file mode 100644 index 0000000000000000000000000000000000000000..721b7e06e7eec9aadfc36b115fdcc9e5a020bb28 --- /dev/null +++ b/pretrained_custom/Rigel_32k_3890220.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfe78c41dc6ec4d8482095c0090bbd1fb8fa84b1ceae73deeca6c5449a76f2d6 +size 1207173025 diff --git a/pretrained_custom/Rigel_32k_fp32_2854856.zip b/pretrained_custom/Rigel_32k_fp32_2854856.zip new file mode 100644 index 0000000000000000000000000000000000000000..e72fd9c10339c5c7e9c3c4c0b3da7c2e6de89e4f --- /dev/null +++ b/pretrained_custom/Rigel_32k_fp32_2854856.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1941fff9c1189a6b8c26cb760a702d73b4bd219b0545138e45b3b1ab61bea633 +size 1206949035 diff --git a/pretrained_custom/Rigel_Portuguese_50e.zip b/pretrained_custom/Rigel_Portuguese_50e.zip new file mode 100644 index 0000000000000000000000000000000000000000..48f4b4c7a8c366ac4794e4b784c7ae77825b94a7 --- /dev/null +++ b/pretrained_custom/Rigel_Portuguese_50e.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a0228afa362ccd80ecc54655d0880c07dabc895414ab6a87245f52f7e8f6e7 +size 1206455414 diff --git a/pretrained_custom/Snowie-X-Rin-40k.zip b/pretrained_custom/Snowie-X-Rin-40k.zip new file mode 100644 index 0000000000000000000000000000000000000000..7daca50fa90942bc195994c9862281c287bf485b --- /dev/null +++ b/pretrained_custom/Snowie-X-Rin-40k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc0c6f5a8da61a0a72e5129f4d122c0fa90ed287571f3187d662d2c67efbcc1b +size 1198314806 diff --git a/pretrained_custom/SnowieV3.1_32k.zip b/pretrained_custom/SnowieV3.1_32k.zip new file mode 100644 index 0000000000000000000000000000000000000000..06dd8c0b728dfe56f28ce4bd083aba753dd64b88 --- /dev/null +++ b/pretrained_custom/SnowieV3.1_32k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceeb2137ce5951475e2bdf083666352591201d8b4bcfe8548b3dabfec69fad0b +size 1203667282 diff --git a/pretrained_custom/SnowieV3.1_40k.zip b/pretrained_custom/SnowieV3.1_40k.zip new file mode 100644 index 0000000000000000000000000000000000000000..e316a1bf9e28e1e668d7343729176e123d0d447b --- /dev/null +++ b/pretrained_custom/SnowieV3.1_40k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eba29cf6b86b8eef6e01fe11c7223dce5f87e0dba31d63d62395fe6ec520c977 +size 1198318779 diff --git a/pretrained_custom/SnowieV3.1_48k.zip b/pretrained_custom/SnowieV3.1_48k.zip new file mode 100644 index 0000000000000000000000000000000000000000..09092d19e31da5460bf01b2fa0fd379540109301 --- /dev/null +++ b/pretrained_custom/SnowieV3.1_48k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a1d309957e6c54695e40df823ebef8e498418173485da61f168c3468ee70127 +size 1210892038 diff --git a/pretrained_custom/Snowie_RuPretrain_48k_V1.2.zip b/pretrained_custom/Snowie_RuPretrain_48k_V1.2.zip new file mode 100644 index 0000000000000000000000000000000000000000..b62b80cedbd535f0bfc619f21bfe4945f35c3ee5 --- /dev/null +++ b/pretrained_custom/Snowie_RuPretrain_48k_V1.2.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5957cf9f65c4e1d2e08ef1d699238e80367b144cb29fd874df861e4d998c10fc +size 1209365692 diff --git a/pretrained_custom/Snowie_RuPretrain_EnP.zip b/pretrained_custom/Snowie_RuPretrain_EnP.zip new file mode 100644 index 0000000000000000000000000000000000000000..f156fc0dbeefce759112360b8339abef1ffdb845 --- /dev/null +++ b/pretrained_custom/Snowie_RuPretrain_EnP.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe03ea12a23d69f62c9e52cee984d75c8e4c0a6226b1f793fcd1c37fe1ae40e4 +size 1197840839 diff --git a/pretrained_custom/UKA.zip b/pretrained_custom/UKA.zip new file mode 100644 index 0000000000000000000000000000000000000000..0a1076ff7c8e1ade516afc376eed2ef859c33e14 --- /dev/null +++ b/pretrained_custom/UKA.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:122f7dca3518f4f5722cf4f1d235df3bc31bdc4d0893765ad4e3c2f88997c7e0 +size 1201794774 diff --git a/pretrained_custom/f0Ov2Super32k.zip b/pretrained_custom/f0Ov2Super32k.zip new file mode 100644 index 0000000000000000000000000000000000000000..d6acd1089132436d7df57f50e040d3cbeae6059b --- /dev/null +++ b/pretrained_custom/f0Ov2Super32k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79a163b384e5f679f8e183d2e10899739346f4f4f72cfa578a20463c4b8478a2 +size 1202234643 diff --git a/pretrained_custom/f0Ov2Super40k.zip b/pretrained_custom/f0Ov2Super40k.zip new file mode 100644 index 0000000000000000000000000000000000000000..7ebb2921536cf6b161a44be7c9b9e0dcbc54ef3d --- /dev/null +++ b/pretrained_custom/f0Ov2Super40k.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba0707db42b13fe840abd8fa9bac467e72a4556cbfd0d3eb412f0105cb51300e +size 1198085924 diff --git a/pretrained_custom/nanashi_anime_384e.zip b/pretrained_custom/nanashi_anime_384e.zip new file mode 100644 index 0000000000000000000000000000000000000000..410321013f769fe809ff325c131504bf05f4d445 --- /dev/null +++ b/pretrained_custom/nanashi_anime_384e.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e75b321151a6c5b78de947dc0e11b81e8df816081eab5da72cd9e58476fae7e +size 1200927472 diff --git a/pretrained_custom/nanashi_anime_resized.zip b/pretrained_custom/nanashi_anime_resized.zip new file mode 100644 index 0000000000000000000000000000000000000000..b7763a558d135bf6204434d4a3c5918f3a883b13 --- /dev/null +++ b/pretrained_custom/nanashi_anime_resized.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac25e01549c085d9afcffd794cb84508137fdcc3547b65d0d241a808dd6d9d6e +size 200357232 diff --git a/pretrained_custom/nanashi_v1.5.zip b/pretrained_custom/nanashi_v1.5.zip new file mode 100644 index 0000000000000000000000000000000000000000..9464cc67d36514af1a9ecdafe09831f2bc14f6ab --- /dev/null +++ b/pretrained_custom/nanashi_v1.5.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cb2738608f75d0337b6dc87c9c4ae4fbc8aaf1d949fbc01f63cd9086d7adcf9 +size 1200294956 diff --git a/pretrained_custom/nanashi_v1.7.zip b/pretrained_custom/nanashi_v1.7.zip new file mode 100644 index 0000000000000000000000000000000000000000..f1af3809fabcb1631416b47a16cd56145ccb06ad --- /dev/null +++ b/pretrained_custom/nanashi_v1.7.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dfb4dfdc4a92ee69d876223dfe91de4cfaf00e8597aaa4d90b5cff12b25d903 +size 1201609808 diff --git a/pretrained_custom/nanashi_v1.zip b/pretrained_custom/nanashi_v1.zip new file mode 100644 index 0000000000000000000000000000000000000000..67f9a978a6d59323dadfbcf0f4cdcd07d7acf792 --- /dev/null +++ b/pretrained_custom/nanashi_v1.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11f3298f0523956b0ab0df328753fc0c95db205a20a2e1146ad1bd63f11ca5ec +size 1203415435 diff --git a/pretrained_custom/nanashi_v2_base.zip b/pretrained_custom/nanashi_v2_base.zip new file mode 100644 index 0000000000000000000000000000000000000000..f14829ccdbd44138ff4dcbfca4b1c2384053bab1 --- /dev/null +++ b/pretrained_custom/nanashi_v2_base.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f015245367dbb6030717d2c514699d5214b209c99b9769606850dff7f932d967 +size 1202681341 diff --git a/pretrained_custom/nanashi_v2_finetune.zip b/pretrained_custom/nanashi_v2_finetune.zip new file mode 100644 index 0000000000000000000000000000000000000000..fc2e7b712cef12b2fdcbd05891b49c34d0ee5065 --- /dev/null +++ b/pretrained_custom/nanashi_v2_finetune.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90e908eec4c971625c56ca98d6a2ddb6303aa440c6acfbbb34f4031fd93fd681 +size 1203816689 diff --git a/pretrained_v1/D32k.pth b/pretrained_v1/D32k.pth new file mode 100644 index 0000000000000000000000000000000000000000..346293c7023f67178a4c85da94cc3e85bdb320ef --- /dev/null +++ b/pretrained_v1/D32k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ab20645829460fdad0d3c44254f1ab53c32cae50c22a66c926ae5aa30abda6f +size 109978943 diff --git a/pretrained_v1/D40k.pth b/pretrained_v1/D40k.pth new file mode 100644 index 0000000000000000000000000000000000000000..11fd6ad63daeb5d786e78d843a6f0800c3d2394c --- /dev/null +++ b/pretrained_v1/D40k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:547f66dbbcd9023b9051ed244d12ab043ba8a4e854b154cc28761ac7c002909b +size 109978943 diff --git a/pretrained_v1/D48k.pth b/pretrained_v1/D48k.pth new file mode 100644 index 0000000000000000000000000000000000000000..48beafd328bedd8cf493bbf5f4a9d37d2260024a --- /dev/null +++ b/pretrained_v1/D48k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cc013fa60ed9c3f902f5bd99f48c7e3b9352d763d4d3cd6bc241c37b0bfd9ad +size 109978943 diff --git a/pretrained_v1/G32k.pth b/pretrained_v1/G32k.pth new file mode 100644 index 0000000000000000000000000000000000000000..e64d79fd69b7287cdac27cd31dbdfd62c563e094 --- /dev/null +++ b/pretrained_v1/G32k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81817645cde7ed2e2d83f23ef883f33dda564924b497e84d792743912eca4c23 +size 72653893 diff --git a/pretrained_v1/G40k.pth b/pretrained_v1/G40k.pth new file mode 100644 index 0000000000000000000000000000000000000000..16796af627338b8c55934df239be3b9d27f9f060 --- /dev/null +++ b/pretrained_v1/G40k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e428573bda1124b0ae0ae843fd8dcded6027d3993444790b3e9b0100938b2113 +size 72763063 diff --git a/pretrained_v1/G48k.pth b/pretrained_v1/G48k.pth new file mode 100644 index 0000000000000000000000000000000000000000..509a033306a137648a4f59e6016097b7bd318dd8 --- /dev/null +++ b/pretrained_v1/G48k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3862a67ea6313e8ffefc05cee6bee656ef3e089442e9ecf4a6618d60721f3e95 +size 72850501 diff --git a/pretrained_v1/f0D32k.pth b/pretrained_v1/f0D32k.pth new file mode 100644 index 0000000000000000000000000000000000000000..9f36ffb9c4afdf77440f4619688d985daa25b107 --- /dev/null +++ b/pretrained_v1/f0D32k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:294db3087236e2c75260d6179056791c9231245daf5d0485545d9e54c4057c77 +size 109978943 diff --git a/pretrained_v1/f0D40k.pth b/pretrained_v1/f0D40k.pth new file mode 100644 index 0000000000000000000000000000000000000000..da7dad91a825dac3a2ed0fb418c99be4a804811e --- /dev/null +++ b/pretrained_v1/f0D40k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d4f5a441594b470d67579958b2fd4c6b992852ded28ff9e72eda67abcebe423 +size 109978943 diff --git a/pretrained_v1/f0D48k.pth b/pretrained_v1/f0D48k.pth new file mode 100644 index 0000000000000000000000000000000000000000..789032e0a223731da818f55c6f65df22a354d6e3 --- /dev/null +++ b/pretrained_v1/f0D48k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b84c8bf347ad1e539c842e8f2a4c36ecd9e7fb23c16041189e4877e9b07925c +size 109978943 diff --git a/pretrained_v1/f0G32k.pth b/pretrained_v1/f0G32k.pth new file mode 100644 index 0000000000000000000000000000000000000000..b425a989fbdccb9821e512e9c0b4d84b80169769 --- /dev/null +++ b/pretrained_v1/f0G32k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:285f524bf48bb692c76ad7bd0bc654c12bd9e5edeb784dddf7f61a789a608574 +size 72795627 diff --git a/pretrained_v1/f0G40k.pth b/pretrained_v1/f0G40k.pth new file mode 100644 index 0000000000000000000000000000000000000000..a4207034410f808123cfef2ea4aeb2d412f15f72 --- /dev/null +++ b/pretrained_v1/f0G40k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9115654aeef1995f7dd3c6fc4140bebbef0ca9760bed798105a2380a34299831 +size 72909665 diff --git a/pretrained_v1/f0G48k.pth b/pretrained_v1/f0G48k.pth new file mode 100644 index 0000000000000000000000000000000000000000..8da740c01aeb6ec0054b221fa7da4242139b273b --- /dev/null +++ b/pretrained_v1/f0G48k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78bc9cab27e34bcfc194f93029374d871d8b3e663ddedea32a9709e894cc8fe8 +size 73008619 diff --git a/pretrained_v2/D32k.pth b/pretrained_v2/D32k.pth new file mode 100644 index 0000000000000000000000000000000000000000..b55340b0bc2875f148b245e781d534c5dd4f7894 --- /dev/null +++ b/pretrained_v2/D32k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8043378cc6619083d385f5a045de09b83fb3bf8de45c433ca863b71723ac3ca +size 142875703 diff --git a/pretrained_v2/D40k.pth b/pretrained_v2/D40k.pth new file mode 100644 index 0000000000000000000000000000000000000000..6d13aea9208310573b59309a9c80310ef71c5547 --- /dev/null +++ b/pretrained_v2/D40k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:471378e894e7191f89a94eda8288c5947b16bbe0b10c3f1f17efdb7a1d998242 +size 142875703 diff --git a/pretrained_v2/D48k.pth b/pretrained_v2/D48k.pth new file mode 100644 index 0000000000000000000000000000000000000000..2f3b46950856921425d3dd2a0857ce14fc7dc622 --- /dev/null +++ b/pretrained_v2/D48k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db01094a93c09868a278e03dafe8bb781bfcc1a5ba8df168c948bf9168c84d82 +size 142875703 diff --git a/pretrained_v2/G32k.pth b/pretrained_v2/G32k.pth new file mode 100644 index 0000000000000000000000000000000000000000..d34c78904a383344a31fa9814782e55d82d852ae --- /dev/null +++ b/pretrained_v2/G32k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:869b26a47f75168d6126f64ac39e6de5247017a8658cfd68aca600f7323efb9f +size 73811639 diff --git a/pretrained_v2/G40k.pth b/pretrained_v2/G40k.pth new file mode 100644 index 0000000000000000000000000000000000000000..ee39bf64a1fc1d0d8154e242a3b60ef3e2abf0ca --- /dev/null +++ b/pretrained_v2/G40k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3843da7fde33db1dab176146c70d6c2df06eafe9457f4e3aa10024e9c6a4b69 +size 72959671 diff --git a/pretrained_v2/G48k.pth b/pretrained_v2/G48k.pth new file mode 100644 index 0000000000000000000000000000000000000000..71fb5f1037137dae5ae4a5786c452197f3eabab1 --- /dev/null +++ b/pretrained_v2/G48k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e2b1581a436d07a76b10b9d38765f64aa02836dc65c7dee1ce4140c11ea158b +size 75318967 diff --git a/pretrained_v2/RefineGAN_f0D32k.pth b/pretrained_v2/RefineGAN_f0D32k.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a504d40f2bc9a6057e29d548859c7512c659b85 --- /dev/null +++ b/pretrained_v2/RefineGAN_f0D32k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aea04f4116178a842f74c9fb06ded0d4a68640128b67b459a2293a9874fc9a9 +size 285688383 diff --git a/pretrained_v2/RefineGAN_f0D40k.pth b/pretrained_v2/RefineGAN_f0D40k.pth new file mode 100644 index 0000000000000000000000000000000000000000..4b65ade83c4160e1416ebcdc7d87d97e9725ea59 --- /dev/null +++ b/pretrained_v2/RefineGAN_f0D40k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d919ba0ea86a322d36b2d6f62d235b6f66f6cc72004c0f2d1a22417f0f18426 +size 285688383 diff --git a/pretrained_v2/RefineGAN_f0D48k.pth b/pretrained_v2/RefineGAN_f0D48k.pth new file mode 100644 index 0000000000000000000000000000000000000000..66fcb11fd4e9b69823d0348f8b1e8b80038c9373 --- /dev/null +++ b/pretrained_v2/RefineGAN_f0D48k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78ec24112c1ae9d5e80d555f056d25c0620bfd80f3f969c034a331ec846743f8 +size 285688383 diff --git a/pretrained_v2/RefineGAN_f0G32k.pth b/pretrained_v2/RefineGAN_f0G32k.pth new file mode 100644 index 0000000000000000000000000000000000000000..f31be9a830735afa9cfe6a399dfa220b8361c172 --- /dev/null +++ b/pretrained_v2/RefineGAN_f0G32k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:102501f6f5b621a4ea231fabf78c97be21490d63b313c454a9376fad34f65f42 +size 139392266 diff --git a/pretrained_v2/RefineGAN_f0G40k.pth b/pretrained_v2/RefineGAN_f0G40k.pth new file mode 100644 index 0000000000000000000000000000000000000000..91cf72b8429ac025e37e273ac12693fc4a2cc097 --- /dev/null +++ b/pretrained_v2/RefineGAN_f0G40k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec490f83729bcecda97ddcc182dc7f6eab0234ead2e7a8305451f636b0ef0a0b +size 139793674 diff --git a/pretrained_v2/RefineGAN_f0G48k.pth b/pretrained_v2/RefineGAN_f0G48k.pth new file mode 100644 index 0000000000000000000000000000000000000000..315d982c2604c4dd7d00ad9878238972a4f69d9b --- /dev/null +++ b/pretrained_v2/RefineGAN_f0G48k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d7ae7b7ed2e191ec3a5a8b64dad841b90ee7c94357c70926d48fa9d85010e02 +size 139793674 diff --git a/pretrained_v2/f0D32k.pth b/pretrained_v2/f0D32k.pth new file mode 100644 index 0000000000000000000000000000000000000000..7449cc83c3f97fd87c62596f005d262120b64772 --- /dev/null +++ b/pretrained_v2/f0D32k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd7134e7793674c85474d5145d2d982e3c5d8124fc7bb6c20f710ed65808fa8a +size 142875703 diff --git a/pretrained_v2/f0D40k.pth b/pretrained_v2/f0D40k.pth new file mode 100644 index 0000000000000000000000000000000000000000..68e29fb9debf8994f68cb4f31cc4d81d360fb73b --- /dev/null +++ b/pretrained_v2/f0D40k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b6ab091e70801b28e3f41f335f2fc5f3f35c75b39ae2628d419644ec2b0fa09 +size 142875703 diff --git a/pretrained_v2/f0D48k.pth b/pretrained_v2/f0D48k.pth new file mode 100644 index 0000000000000000000000000000000000000000..a9f2b74cdccf9bfc2ebb0be8b481c76552a28661 --- /dev/null +++ b/pretrained_v2/f0D48k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2269b73c7a4cf34da09aea99274dabf99b2ddb8a42cbfb065fb3c0aa9a2fc748 +size 142875703 diff --git a/pretrained_v2/f0G32k.pth b/pretrained_v2/f0G32k.pth new file mode 100644 index 0000000000000000000000000000000000000000..6bff869bb04fae663dddd1fbe5c04b497bfc4209 --- /dev/null +++ b/pretrained_v2/f0G32k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2332611297b8d88c7436de8f17ef5f07a2119353e962cd93cda5806d59a1133d +size 73950049 diff --git a/pretrained_v2/f0G40k.pth b/pretrained_v2/f0G40k.pth new file mode 100644 index 0000000000000000000000000000000000000000..3333a970abc908b4e8afd45c1cc2120ce1b4b0b4 --- /dev/null +++ b/pretrained_v2/f0G40k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b2c44035e782c4b14ddc0bede9e2f4a724d025cd073f736d4f43708453adfcb +size 73106273 diff --git a/pretrained_v2/f0G48k.pth b/pretrained_v2/f0G48k.pth new file mode 100644 index 0000000000000000000000000000000000000000..34d1ec0e2594379989cad7b72991152a9f97d99e --- /dev/null +++ b/pretrained_v2/f0G48k.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5d51f589cc3632d4eae36a315b4179397695042edc01d15312e1bddc2b764a4 +size 75465569 diff --git a/releases/Vietnamese-RVC-amd.zip b/releases/Vietnamese-RVC-amd.zip new file mode 100644 index 0000000000000000000000000000000000000000..c6d1757e8a6d60c4b529c1dbcda0e8a2093d341b --- /dev/null +++ b/releases/Vietnamese-RVC-amd.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34c943de2ea4d35affc87016587ba879bb49d8ff7b6e88d87a165bf170d07953 +size 1297081167 diff --git a/releases/Vietnamese-RVC-cpu.zip b/releases/Vietnamese-RVC-cpu.zip new file mode 100644 index 0000000000000000000000000000000000000000..3d7693ca4760fc8a541732622ccdf0db0c16b70e --- /dev/null +++ b/releases/Vietnamese-RVC-cpu.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7246d40adede60b8bf400b01ade584d8a3ce527aec2c8e7ddf0b3b87e61b5c09 +size 1302228938 diff --git a/releases/Vietnamese-RVC-cuda.zip b/releases/Vietnamese-RVC-cuda.zip new file mode 100644 index 0000000000000000000000000000000000000000..e9b638ca46994800bcbfc334d0fd961b274f1671 --- /dev/null +++ b/releases/Vietnamese-RVC-cuda.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad007892c70f9de0b9dee86ea8ca87744c10cfef72adb4c7a55ef06ae4870117 +size 4358515862 diff --git a/runtime/runtime-amd.zip b/runtime/runtime-amd.zip new file mode 100644 index 0000000000000000000000000000000000000000..e9c85878cda40b34cc3c4ac5a2b55c4960f212ac --- /dev/null +++ b/runtime/runtime-amd.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f94cf6ff8982537b348860451d413fcbc383767d15ecda51e533323f783ceea +size 868333641 diff --git a/runtime/runtime-cpu.zip b/runtime/runtime-cpu.zip new file mode 100644 index 0000000000000000000000000000000000000000..bd5bf5f06cde6aca06cb56f4e5161807f896418c --- /dev/null +++ b/runtime/runtime-cpu.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39e2634f7b97a23bcfb53773ab051ae84084d78d8a5e9a6fa915cd84144de98f +size 874587660 diff --git a/runtime/runtime-nvidia.zip b/runtime/runtime-nvidia.zip new file mode 100644 index 0000000000000000000000000000000000000000..8f6b9ce540bb2c6849c5d55785055e6e2c5add62 --- /dev/null +++ b/runtime/runtime-nvidia.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:651bbf07c47f83f65ddb2c15df00d5875c9078065d6a80f172cd97f99faa4c63 +size 3929762609 diff --git a/speaker_diarization/base.en.pt b/speaker_diarization/base.en.pt new file mode 100644 index 0000000000000000000000000000000000000000..db9e9c2df65fdfb12fdecd8a527e9e973cd9a91d --- /dev/null +++ b/speaker_diarization/base.en.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25a8566e1d0c1e2231d1c762132cd20e0f96a85d16145c3a00adf5d1ac670ead +size 145261783 diff --git a/speaker_diarization/base.pt b/speaker_diarization/base.pt new file mode 100644 index 0000000000000000000000000000000000000000..e74166ad66284edaf11199425e7d3de266af194d --- /dev/null +++ b/speaker_diarization/base.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed3a0b6b1c0edf879ad9b11b1af5a0e6ab5db9205f891f668f8b0e6c6326e34e +size 145262807 diff --git a/speaker_diarization/large-v1.pt b/speaker_diarization/large-v1.pt new file mode 100644 index 0000000000000000000000000000000000000000..304221d31c2b2a48c7d68bc8f0c1dc350f0b7dac --- /dev/null +++ b/speaker_diarization/large-v1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4b87e7e0bf463eb8e6956e646f1e277e901512310def2c24bf0e11bd3c28e9a +size 3086999982 diff --git a/speaker_diarization/large-v2.pt b/speaker_diarization/large-v2.pt new file mode 100644 index 0000000000000000000000000000000000000000..67a128bf459fa3789f20a2804b45cd9cf6b08d04 --- /dev/null +++ b/speaker_diarization/large-v2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524 +size 3086999982 diff --git a/speaker_diarization/large-v3-turbo.pt b/speaker_diarization/large-v3-turbo.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d9ae1a30ec3630012575da687237ac1570abc1b --- /dev/null +++ b/speaker_diarization/large-v3-turbo.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aff26ae408abcba5fbf8813c21e62b0941638c5f6eebfb145be0c9839262a19a +size 1617941637 diff --git a/speaker_diarization/large-v3.pt b/speaker_diarization/large-v3.pt new file mode 100644 index 0000000000000000000000000000000000000000..eb02b93ec126f160e482aa0f63ef50a35ff7cdbd --- /dev/null +++ b/speaker_diarization/large-v3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb +size 3087371615 diff --git a/speaker_diarization/medium.en.pt b/speaker_diarization/medium.en.pt new file mode 100644 index 0000000000000000000000000000000000000000..70e9bc35d38faa711ce7bb4ce1edae6566b8facd --- /dev/null +++ b/speaker_diarization/medium.en.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7440d1dc186f76616474e0ff0b3b6b879abc9d1a4926b7adfa41db2d497ab4f +size 1528006491 diff --git a/speaker_diarization/medium.pt b/speaker_diarization/medium.pt new file mode 100644 index 0000000000000000000000000000000000000000..8aca41c710014a3d39774cd7592fa086177c672f --- /dev/null +++ b/speaker_diarization/medium.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1 +size 1528008539 diff --git a/speaker_diarization/small.en.pt b/speaker_diarization/small.en.pt new file mode 100644 index 0000000000000000000000000000000000000000..e08c38233bc569607ba330966482125a257769c3 --- /dev/null +++ b/speaker_diarization/small.en.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f953ad0fd29cacd07d5a9eda5624af0f6bcf2258be67c92b79389873d91e0872 +size 483615683 diff --git a/speaker_diarization/small.pt b/speaker_diarization/small.pt new file mode 100644 index 0000000000000000000000000000000000000000..119531e7096f24eb87b1bf339dfd34a5124a98bd --- /dev/null +++ b/speaker_diarization/small.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ecf779972d90ba49c06d968637d720dd632c55bbf19d441fb42bf17a411e794 +size 483617219 diff --git a/speaker_diarization/speechbrain/classifier.ckpt b/speaker_diarization/speechbrain/classifier.ckpt new file mode 100644 index 0000000000000000000000000000000000000000..d6f70f222826ea5490bfad657373af3d6d2a08ba --- /dev/null +++ b/speaker_diarization/speechbrain/classifier.ckpt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd9e3634fe68bd0a427c95e354c0c677374f62b3f434e45b78599950d860d535 +size 5534328 diff --git a/speaker_diarization/speechbrain/config.json b/speaker_diarization/speechbrain/config.json new file mode 100644 index 0000000000000000000000000000000000000000..2e8b3b4d97ae58d7daa78954a5c7f5b8abb42934 --- /dev/null +++ b/speaker_diarization/speechbrain/config.json @@ -0,0 +1,3 @@ +{ + "speechbrain_interface": "SpeakerRecognition" +} \ No newline at end of file diff --git a/speaker_diarization/speechbrain/embedding_model.ckpt b/speaker_diarization/speechbrain/embedding_model.ckpt new file mode 100644 index 0000000000000000000000000000000000000000..8ba959669e5570dbbf8076bc6b8a79555a81d5c4 --- /dev/null +++ b/speaker_diarization/speechbrain/embedding_model.ckpt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0575cb64845e6b9a10db9bcb74d5ac32b326b8dc90352671d345e2ee3d0126a2 +size 83316686 diff --git a/speaker_diarization/speechbrain/hyperparams.yaml b/speaker_diarization/speechbrain/hyperparams.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7e9865b143e4343ed2ff49392ef6c7740fcd54df --- /dev/null +++ b/speaker_diarization/speechbrain/hyperparams.yaml @@ -0,0 +1,58 @@ +# ############################################################################ +# Model: ECAPA big for Speaker verification +# ############################################################################ + +# Feature parameters +n_mels: 80 + +# Pretrain folder (HuggingFace) +pretrained_path: assets/models/speaker_diarization/models/speechbrain + +# Output parameters +out_n_neurons: 7205 + +# Model params +compute_features: !new:main.library.speaker_diarization.features.Fbank + n_mels: !ref