Open shuaijiang opened 1 month ago
I try the instruct mode to synthesis the audio according to the instruct text, but the audio also contain the intruct text
from cosyvoice.cli.cosyvoice import CosyVoice import torchaudio cosyvoice = CosyVoice('iic/CosyVoice-300M-Instruct') output = cosyvoice.inference_instruct('在面对挑战时,他展现了非凡的勇气与智慧。', '中文男', '女声,快语速') torchaudio.save('instruct.wav', output['tts_speech'], 22050)
I tried the same code but didn't see the problem, try again
thx, I get the point. The instruct text don't support Chinese?
I try the instruct mode to synthesis the audio according to the instruct text, but the audio also contain the intruct text