Update cosyvoice/cli/model.py

cosyvoice/cli/model.py

@@ -395,7 +395,7 @@ class CosyVoice3Model(CosyVoice2Model):
         # NOTE must matching training static_chunk_size
         self.token_hop_len = 25
         # rtf and decoding related
-        self.llm_context = torch.cuda.stream(torch.cuda.Stream(self.device)) if torch.cuda.is_available() else nullcontext()
+        self.llm_context = nullcontext()
         self.lock = threading.Lock()
         # dict used to store session related variable
         self.tts_speech_token_dict = {}