驻马店市政府采购电子商城_b2b电子商务网站介绍_域名查询大全_聊城seo整站优化报价

结构如图

代码如下：

import ChatTTS
import torch
import torchaudiochat = ChatTTS.Chat()
chat.load(compile=False) # Set to True for better performancetexts = ["PUT YOUR 1st TEXT HERE", "PUT YOUR 2nd TEXT HERE"]wavs = chat.infer(texts)for i in range(len(wavs)):"""In some versions of torchaudio, the first line works but in other versions, so does the second line."""try:torchaudio.save(f"basic_output{i}.wav", torch.from_numpy(wavs[i]).unsqueeze(0), 24000)except:torchaudio.save(f"basic_output{i}.wav", torch.from_numpy(wavs[i]), 24000)

运行如下：

(chattts) duyicheng@duyicheng-computer:~/gitee/ChatTTS$ python base.py
found invalid characters: {'1'}
found invalid characters: {'2'}
text:   0%|▍                                                                                                                                                                                     | 1/384(max) [00:00,  2.24it/s]We detected that you are passing `past_key_values` as a tuple of tuples. This is deprecated and will be removed in v4.47. Please convert your cache or use an appropriate `Cache` class (https://huggingface.co/docs/transformers/kv_cache#legacy-cache-format)
text:   3%|████▋                                                                                                                                                                                | 10/384(max) [00:00, 13.17it/s]
code:   4%|██████▊                                                                                                                                                                             | 77/2048(max) [00:02, 31.63it/s]
(chattts) duyicheng@duyicheng-computer:~/gitee/ChatTTS$

 音质还行。