jianchang512 / ChatTTS-ui

一个简单的本地网页界面,使用ChatTTS将文字合成为语音,同时支持对外提供API接口。A simple native web interface that uses ChatTTS to synthesize text into speech, along with support for external API interfaces.
https://pyvideotrans.com
Other
5.04k stars 549 forks source link

py软件里的一个短句超过WARNING:ChatTTS.model.gpt:Incomplete result. hit max_new_token: 384 #87

Open lin16303 opened 4 weeks ago

lin16303 commented 4 weeks ago

voice=289,custom_voice=0 固定音色 seed=289 result=['你好'],len=1 0%| | 0/384 [00:00<?, ?it/s]voice=289,custom_voice=0 固定音色 seed=289 result=['好,我...... 我在家里闲逛'],len=1 1%|█ | 5/384 [00:00<00:08, 43.69it/s] 1%|▋ | 18/2048 [00:00<00:44, 45.89it/s] 推理时长: 0.54 秒 | 23/384 [00:00<00:07, 49.11it/s] 音频时长: 0.37 秒 100%|████████████████████████████████████████████████████████████████████████████████| 384/384 [00:04<00:00, 77.23it/s] WARNING:ChatTTS.model.gpt:Incomplete result. hit max_new_token: 384█████████████████▌| 382/384 [00:04<00:00, 79.49it/s] 100%|██████████████████████████████████████████████████████████████████████████████| 2048/2048 [00:27<00:00, 74.76it/s] WARNING:ChatTTS.model.gpt:Incomplete result. hit max_new_token: 2048 推理时长: 32.4 秒 音频时长: 43.68 秒

lin16303 commented 4 weeks ago

是否可以在pyvideotrans的ini设置里加一个跳过refine text选项