update

app.py

@@ -221,7 +221,7 @@ if __name__ == '__main__':
     load_trt = True if os.environ.get('trt') == '1' else False
     logging.info('cosyvoice args load_jit {} load_onnx {} load_trt {}'.format(load_jit, load_onnx, load_trt))
     cosyvoice = CosyVoice2('pretrained_models/CosyVoice2-0.5B', load_jit=load_jit, load_onnx=load_onnx, load_trt=load_trt)
-    sft_spk = cosyvoice.list_avaliable_spks()
+    # sft_spk = cosyvoice.list_avaliable_spks()
     prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
     for stream in [True, False]:
         for i, j in enumerate(cosyvoice.inference_zero_shot('收到好友从远方寄来的生日礼物，那份意外的惊喜与深深的祝福让我心中充满了甜蜜的快乐，笑容如花儿般绽放。', '希望你以后能够做的比我还好呦。', prompt_speech_16k, stream=stream)):

requirements.txt

@@ -34,8 +34,8 @@ tensorboard==2.14.0
 tensorrt-cu12==10.0.1; sys_platform == 'linux'
 tensorrt-cu12-bindings==10.0.1; sys_platform == 'linux'
 tensorrt-cu12-libs==10.0.1; sys_platform == 'linux'
-torch
-torchaudio
+torch==2.4.0
+torchaudio==2.4.0
 transformers==4.40.1
 uvicorn==0.30.0
 wget