search

Plachtaa / VITS-fast-fine-tuning

This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion
Apache License 2.0
4.69k stars 705 forks source link

模型重新训练时报错D:\AItool\VITS_fast_finetune\mel_processing.py:96: FutureWarning: Pass sr=22050, n_fft=1024, n_mels=80, fmin=0.0, fmax=None as keyword args. From version 0.10 passing these as positional arguments will result in an error mel = librosa_mel_fn(sampling_rate, n_fft, num_mels, fmin, fmax) #481

Closed youyi0218 closed 11 months ago

youyi0218 commented 11 months ago

:\AItool\VITS_fast_finetune\mel_processing.py:78: FutureWarning: Pass sr=22050, n_fft=1024, n_mels=80, fmin=0.0, fmax=None as keyword args. From version 0.10 passing these as positional arguments will result in an error mel = librosa_mel_fn(sampling_rate, n_fft, num_mels, fmin, fmax) D:\AItool\VITS_fast_finetune\mel_processing.py:96: FutureWarning: Pass sr=22050, n_fft=1024, n_mels=80, fmin=0.0, fmax=None as keyword args. From version 0.10 passing these as positional arguments will result in an error mel = librosa_mel_fn(sampling_rate, n_fft, num_mels, fmin, fmax) 之前训练的模型跑到二十多跑一半就关了，然后回来重新训练就开始报错 QQ截图20231014154600

youyi0218 commented 11 months ago

2 3 等了亿会，看样子是跑起来了， image 现在you'shua又双叒叕报错了:(

youyi0218 commented 11 months ago

好了我是伞兵，第一个那不是报错，只是单纯的显卡差没有进度，第二个是跑的爆显存了