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 README.md

Browse Source
This commit is contained in:
刘悦
2024-07-22 15:58:41 +08:00
committed by GitHub
parent 9b7c915760
commit 6f6ad85f30
1 changed files with 1 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@@ -80,7 +80,7 @@ export PYTHONPATH=third_party/Matcha-TTS
``` python ``` python
from cosyvoice.cli.cosyvoice import CosyVoice from cosyvoice.cli.cosyvoice import CosyVoice
from cosyvoice.utils.file_utils import load_wav,speed_change from cosyvoice.utils.file_utils import load_wav
import torchaudio import torchaudio
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT') cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT')
@@ -89,10 +89,6 @@ 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') 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) torchaudio.save('sft.wav', output['tts_speech'], 22050)
# if you wanna change the speed
audio,sample_rate = speed_change(output["tts_speech"],22050,"1.6")
torchaudio.save('sft_speed_1.6.wav',audio, 22050)
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M') cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M')
# zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean # zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean
prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000) prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)