CosyVoice再升级，可扩展流式语音合成

modelscope download --model iic/CosyVoice2-0.5B

#模型下载from modelscope import snapshot_downloadmodel_dir = snapshot_download('iic/CosyVoice2-0.5B')

git clone --recursive https://github.com/FunAudioLLM/CosyVoice.git# If you failed to clone submodule due to network failures, please run following command until successcd CosyVoicegit submodule update --init --recursivepip install -r requirements.txt

from modelscope import snapshot_downloadsnapshot_download('iic/CosyVoice2-0.5B', local_dir='pretrained_models/CosyVoice2-0.5B')

export PYTHONPATH=third_party/Matcha-TTS

from cosyvoice.cli.cosyvoice import CosyVoice, CosyVoice2from cosyvoice.utils.file_utils import load_wavimport torchaudiocosyvoice = CosyVoice2('pretrained_models/CosyVoice2-0.5B', load_jit=True, load_onnx=False, load_trt=False)# zero_shot usageprompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)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'], cosyvoice.sample_rate)# fine grained control, for supported control, check cosyvoice/tokenizer/tokenizer.py#L248prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)for i, j in enumerate(cosyvoice.inference_cross_lingual('在他讲述那个荒诞故事的过程中，他突然[laughter]停下来，因为他自己也被逗笑了[laughter]。', prompt_speech_16k, stream=False)):    torchaudio.save('fine_grained_control_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)# instruct usagefor i, j in enumerate(cosyvoice.inference_instruct2('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。', '用四川话说这句话', prompt_speech_16k, stream=False)):    torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)

git clone https://www.modelscope.cn/studios/iic/CosyVoice2-0.5B.git

cd CosyVoice2-0.5Bpip install -r requirements.txtpython app.py