使用Cosyvoice2进行情感语音合成

[zhanghanweii]

在按照论文中的方式合成情感音频时无效，论文中的样例如下：

• 你能用高兴的情感说吗？< |endofprompt| >今天真是太开心了，马上要放假了！I’m so happy, Spring Festival is coming!

我的代码如下：
import sys
sys.path.append("third_party/Matcha-TTS")
from cosyvoice.cli.cosyvoice import CosyVoice, CosyVoice2
from cosyvoice.utils.file_utils import load_wav
import torchaudio

cosyvoice = CosyVoice2('./CosyVoice2-0.5B', load_jit=False, load_trt=False)

cosyvoice = CosyVoice('./pretrained_models/CosyVoice-300M-Instruct')

prompt_speech_16k = load_wav('xiaojin_5s.wav', 16000)

for i, j in enumerate(cosyvoice.inference_cross_lingual('你能用安慰的情感说吗？同时语速放缓。< |endofprompt| >哎呀，没有抢到回家的票真的会让人很失落呢
，但希望你打起精神，一定还会有其他回家的方法的。', prompt_speech_16k, stream=False)):
torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)

上述代码会把整段txt文本进行合成，而没有使用情感描述，请问代码有哪些问题呢

[Aydous]

cosyvoice.inference_instruct2('哎呀，没有抢到回家的票真的会让人很失落呢，但希望你打起精神，一定还会有其他回家的方法的。', '你能用安慰的情感说吗？同时语速放缓', prompt_speech_16k, stream=False)
试试这个

[github-actions]

This issue is stale because it has been open for 30 days with no activity.

[github-actions]

This issue was closed because it has been inactive for 14 days since being marked as stale.