[2noise/ChatTTS]在Intel芯片的MacBook Pro上运行失败

WARNING:ChatTTS.utils.gpu_utils:No GPU found, use CPU instead INFO:ChatTTS.core:use cpu WARNING:ChatTTS.core:vocos not initialized. WARNING:ChatTTS.core:gpt not initialized. WARNING:ChatTTS.core:tokenizer not initialized. WARNING:ChatTTS.core:dvae not initialized. WARNING:ChatTTS.core:vocos not initialized. WARNING:ChatTTS.core:gpt not initialized. WARNING:ChatTTS.core:tokenizer not initialized. WARNING:ChatTTS.core:decoder not initialized. Traceback (most recent call last): File "/private/tmp/demo.py", line 9, in wavs = chat.infer(texts, use_decoder=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/Jacky/.venv/default/lib/python3.12/site-packages/ChatTTS/core.py", line 95, in infer assert self.check_model(use_decoder=use_decoder) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ AssertionError

JackyChan

您需要先下载模型，然后在chat.load_models()时给出模型路径。

这是我生成音频并输出到文件的脚本

import ChatTTS
import numpy as np

model_path = '/Users/zouguodong/.cache/modelscope/hub/pzc163/chatTTS'

chat = ChatTTS.Chat()
chat.load_models(
    vocos_config_path=f"{model_path}/vocos.yaml",
    vocos_ckpt_path=f"{model_path}/Vocos.pt",
    dvae_config_path=f"{model_path}/dvae.yaml",
    dvae_ckpt_path=f"{model_path}/DVAE.pt",
    gpt_config_path=f"{model_path}/gpt.yaml",
    gpt_ckpt_path=f"{model_path}/GPT.pt",
    decoder_config_path=f"{model_path}/decoder.yaml",
    decoder_ckpt_path=f"{model_path}/Decoder.pt",
    tokenizer_path=f"{model_path}/tokenizer.pt",
    device='cpu'
)

texts = ["Complaint", ]

wavs = chat.infer(texts, use_decoder=True)
audio_data = wavs[0]
audio_rate = 24000

# Convert numpy array to bytes
audio_data = (audio_data * 32767).astype(np.int16).tobytes()

# Save audio to file
output_filename = 'output_audio.wav'
with wave.open(output_filename, 'w') as wav_file:
    wav_file.setnchannels(1)  # Mono channel
    wav_file.setsampwidth(2)  # 2 bytes per sample (16-bit audio)
    wav_file.setframerate(audio_rate)
    wav_file.writeframes(audio_data)

print(f"Audio saved to {output_filename}")

zou8944

发现感叹号、”-“会读出来，大家遇到过吗？

violet17

文件保存到哪里去了？找不到呀

niuroumiantt

根据 @zou8944 的说明构建：

确保您的系统上安装了 Git LFS，然后执行git clone https://www.modelscope.cn/pzc163/chatTTS.git并指向模型，如下所示：

cwd = os.getcwd()
model_path = cwd + '/chatTTS'

chat.load_models(
    vocos_config_path=f"{model_path}/config/vocos.yaml",
    vocos_ckpt_path=f"{model_path}/asset/Vocos.pt",
    dvae_config_path=f"{model_path}/config/dvae.yaml",
    dvae_ckpt_path=f"{model_path}/asset/DVAE.pt",
    gpt_config_path=f"{model_path}/config/gpt.yaml",
    gpt_ckpt_path=f"{model_path}/asset/GPT.pt",
    decoder_config_path=f"{model_path}/config/decoder.yaml",
    decoder_ckpt_path=f"{model_path}/asset/Decoder.pt",
    tokenizer_path=f"{model_path}/asset/tokenizer.pt",
    device='cpu'
)

benjamingwynn

[2noise/ChatTTS]在Intel芯片的MacBook Pro上运行失败

回答