update

README.md

@@ -124,8 +124,8 @@ from cosyvoice.utils.file_utils import load_wav
 import torchaudio
 
 ## cosyvoice2 usage
-cosyvoice2 = CosyVoice('pretrained_models/CosyVoice-300M-SFT', load_jit=False, load_onnx=False, load_trt=False)
-# sft usage
+cosyvoice2 = CosyVoice('pretrained_models/CosyVoice2-0.5B', load_jit=False, load_onnx=False, load_trt=False)
+# zero_shot usage
 prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
 for i, j in enumerate(cosyvoice2.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=True)):
     torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice2.sample_rate)

cosyvoice/cli/cosyvoice.py

@@ -128,7 +128,7 @@ class CosyVoice2(CosyVoice):
         if not os.path.exists(model_dir):
             model_dir = snapshot_download(model_dir)
         with open('{}/cosyvoice.yaml'.format(model_dir), 'r') as f:
-            configs = load_hyperpyyaml(f)
+            configs = load_hyperpyyaml(f, overrides={'qwen_pretrain_path': os.path.join(model_dir, 'Qwen2-0.5B-CosyVoice-BlankEN')})
         self.frontend = CosyVoiceFrontEnd(configs['get_tokenizer'],
                                           configs['feat_extractor'],
                                           '{}/campplus.onnx'.format(model_dir),

requirements.txt

@@ -1,4 +1,5 @@
 --extra-index-url https://download.pytorch.org/whl/cu121
+--extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/pypi/simple/ # https://github.com/microsoft/onnxruntime/issues/21684
 conformer==0.3.2
 deepspeed==0.14.2; sys_platform == 'linux'
 diffusers==0.27.2