1024T

请问，Speaker Interpolation 混合那几个权重参数？flow_embedding和llm_embedding吗？

偶尔触发CUDA error: device-side assert triggered，频率还挺高

8

cosyvoice/cli/model.py", line 108, in token2wav token_len=torch.tensor([token.shape[1]], dtype=torch.int32).to(self.device), RuntimeError: CUDA error: device-side assert triggered Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.