deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-05 01:49:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

update modelscope model

Browse Source
This commit is contained in:
lyuxiang.lx
2024-07-06 01:53:58 +08:00
parent 0379f38dd9
commit 834053940d
2 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@@ -40,18 +40,18 @@ If you are expert in this field, and you are only interested in training your ow
``` python
# SDK模型下载
from modelscope import snapshot_download
snapshot_download('speech_tts/CosyVoice-300M', local_dir='pretrained_models/CosyVoice-300M')
snapshot_download('speech_tts/CosyVoice-300M-SFT', local_dir='pretrained_models/CosyVoice-300M-SFT')
snapshot_download('speech_tts/CosyVoice-300M-Instruct', local_dir='pretrained_models/CosyVoice-300M-Instruct')
snapshot_download('iic/CosyVoice-300M', local_dir='pretrained_models/CosyVoice-300M')
snapshot_download('iic/CosyVoice-300M-SFT', local_dir='pretrained_models/CosyVoice-300M-SFT')
snapshot_download('iic/CosyVoice-300M-Instruct', local_dir='pretrained_models/CosyVoice-300M-Instruct')
snapshot_download('speech_tts/speech_kantts_ttsfrd', local_dir='pretrained_models/speech_kantts_ttsfrd')
```
``` sh
# git模型下载，请确保已安装git lfs
mkdir -p pretrained_models
git clone https://www.modelscope.cn/speech_tts/CosyVoice-300M.git pretrained_models/CosyVoice-300M
git clone https://www.modelscope.cn/speech_tts/CosyVoice-300M-SFT.git pretrained_models/CosyVoice-300M-SFT
git clone https://www.modelscope.cn/speech_tts/CosyVoice-300M-Instruct.git pretrained_models/CosyVoice-300M-Instruct
git clone https://www.modelscope.cn/iic/CosyVoice-300M.git pretrained_models/CosyVoice-300M
git clone https://www.modelscope.cn/iic/CosyVoice-300M-SFT.git pretrained_models/CosyVoice-300M-SFT
git clone https://www.modelscope.cn/iic/CosyVoice-300M-Instruct.git pretrained_models/CosyVoice-300M-Instruct
git clone https://www.modelscope.cn/speech_tts/speech_kantts_ttsfrd.git pretrained_models/speech_kantts_ttsfrd
```

2
cosyvoice/cli/frontend.py
View File

@@ -42,7 +42,7 @@ class CosyVoiceFrontEnd:
option.graph_optimization_level = onnxruntime.GraphOptimizationLevel.ORT_ENABLE_ALL
option.intra_op_num_threads = 1
self.campplus_session = onnxruntime.InferenceSession(campplus_model, sess_options=option, providers=["CPUExecutionProvider"])
self.speech_tokenizer_session = onnxruntime.InferenceSession(speech_tokenizer_model, sess_options=option, providers=["CUDAExecutionProvider", "CPUExecutionProvider"])
self.speech_tokenizer_session = onnxruntime.InferenceSession(speech_tokenizer_model, sess_options=option, providers=["CUDAExecutionProvider"if torch.cuda.is_available() else "CPUExecutionProvider"])
if os.path.exists(spk2info):
self.spk2info = torch.load(spk2info, map_location=self.device)
self.instruct = instruct