update stream code

This commit is contained in:
lyuxiang.lx
2024-07-30 16:11:28 +08:00
parent 02f941d348
commit f4e70e222c
15 changed files with 182 additions and 109 deletions

View File

@@ -86,23 +86,24 @@ import torchaudio
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT')
# sft usage
print(cosyvoice.list_avaliable_spks())
output = 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')
torchaudio.save('sft.wav', output['tts_speech'], 22050)
# 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)
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M')
# zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean
prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
output = 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)
torchaudio.save('zero_shot.wav', output['tts_speech'], 22050)
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)
# cross_lingual usage
prompt_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
output = 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)
torchaudio.save('cross_lingual.wav', output['tts_speech'], 22050)
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)
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-Instruct')
# instruct usage, support <laughter></laughter><strong></strong>[laughter][breath]
output = 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.')
torchaudio.save('instruct.wav', output['tts_speech'], 22050)
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)
```
**Start web demo**
@@ -133,10 +134,10 @@ docker build -t cosyvoice:v1.0 .
# change iic/CosyVoice-300M to iic/CosyVoice-300M-Instruct if you want to use instruct inference
# for grpc usage
docker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c "cd /opt/CosyVoice/CosyVoice/runtime/python/grpc && python3 server.py --port 50000 --max_conc 4 --model_dir iic/CosyVoice-300M && sleep infinity"
python3 grpc/client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>
cd grpc && python3 client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>
# for fastapi usage
docker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c "cd /opt/CosyVoice/CosyVoice/runtime/python/fastapi && MODEL_DIR=iic/CosyVoice-300M fastapi dev --port 50000 server.py && sleep infinity"
python3 fastapi/client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>
cd fastapi && python3 client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>
```
## Discussion & Communication