Update cosyvoice/hifigan/generator.py

cosyvoice/hifigan/generator.py

@@ -714,7 +714,7 @@ class CausalHiFTGenerator(HiFTGenerator):
     @torch.inference_mode()
     def inference(self, speech_feat: torch.Tensor, finalize: bool = True) -> torch.Tensor:
         # mel->f0 NOTE f0_predictor precision is crucial for causal inference, move self.f0_predictor to cpu if necessary
-        f0 = self.f0_predictor(speech_feat, finalize=finalize).to(speech_feat)
+        f0 = self.f0_predictor(speech_feat.cuda(), finalize=finalize)
         # f0->source
         s = self.f0_upsamp(f0[:, None]).transpose(1, 2)  # bs,n,t
         s, _, _ = self.m_source(s)