deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-04 17:39:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
lyuxiang.lx
2024-12-12 15:43:17 +08:00
parent 0bf706c26f
commit 2345ce6be2
4 changed files with 19 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@@ -116,27 +116,27 @@ cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT', load_jit=True, loa
print(cosyvoice.list_avaliable_spks())
# change stream=True for chunk stream inference
for i, j in enumerate(cosyvoice.inference_sft('你好，我是通义生成式语音大模型，请问有什么可以帮您的吗？', '中文女', stream=False)):
torchaudio.save('sft_{}.wav'.format(i), j['tts_speech'], 22050)
torchaudio.save('sft_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-25Hz') # or change to pretrained_models/CosyVoice-300M for 50Hz inference
# zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean
prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
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=False)):
torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], 22050)
torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
# cross_lingual usage
prompt_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
for i, j in enumerate(cosyvoice.inference_cross_lingual('<|en|>And then later on, fully acquiring that company. So keeping management in line, interest in line with the asset that\'s coming into the family is a reason why sometimes we don\'t buy the whole thing.', prompt_speech_16k, stream=False)):
torchaudio.save('cross_lingual_{}.wav'.format(i), j['tts_speech'], 22050)
torchaudio.save('cross_lingual_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
# vc usage
prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
source_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
for i, j in enumerate(cosyvoice.inference_vc(source_speech_16k, prompt_speech_16k, stream=False)):
torchaudio.save('vc_{}.wav'.format(i), j['tts_speech'], 22050)
torchaudio.save('vc_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-Instruct')
# instruct usage, support <laughter></laughter><strong></strong>[laughter][breath]
for i, j in enumerate(cosyvoice.inference_instruct('在面对挑战时，他展现了非凡的<strong>勇气</strong>与<strong>智慧</strong>。', '中文男', 'Theo \'Crimson\', is a fiery, passionate rebel leader. Fights with fervor for justice, but struggles with impulsiveness.', stream=False)):
torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], 22050)
torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
```
**Start web demo**