|
|
@@ -80,7 +80,7 @@ export PYTHONPATH=third_party/Matcha-TTS
|
|
|
|
|
|
``` python
|
|
|
from cosyvoice.cli.cosyvoice import CosyVoice
|
|
|
-from cosyvoice.utils.file_utils import load_wav
|
|
|
+from cosyvoice.utils.file_utils import load_wav,speed_change
|
|
|
import torchaudio
|
|
|
|
|
|
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT')
|
|
|
@@ -89,6 +89,10 @@ 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)
|
|
|
|
|
|
+# 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')
|
|
|
# zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean
|
|
|
prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
|
|
|
@@ -156,4 +160,4 @@ You can also scan the QR code to join our official Dingding chat group.
|
|
|
5. We borrowed a lot of code from [WeNet](https://github.com/wenet-e2e/wenet).
|
|
|
|
|
|
## Disclaimer
|
|
|
-The content provided above is for academic purposes only and is intended to demonstrate technical capabilities. Some examples are sourced from the internet. If any content infringes on your rights, please contact us to request its removal.
|
|
|
+The content provided above is for academic purposes only and is intended to demonstrate technical capabilities. Some examples are sourced from the internet. If any content infringes on your rights, please contact us to request its removal.
|
刘悦