vits_chinese
vits_chinese copied to clipboard
PlayVoice
Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!
Hey, Is it possible to adapt this model to train on English dataset? Or should I just use normal VITS?
Hello MaxMax2016, Thank you for sharing your code on the improved VITS, I hope to check with you about the model behaviors when adding the bi-directional KL divergence. In this...
我讲该项目移植到其他项目中，作为工具使用。 文件报错`vits_chinese\monotonic_align\__init__.py", line 3, in ` `from tools.vits_chinese.monotonic_align.core import maximum_path_c ModuleNotFoundError: No module named 'tools.vits_chinese.monotonic_align.core'` 因为迁移的问题，很多文件的导入，使用了绝对路径。 `import numpy as np import torch from tools.vits_chinese.monotonic_align.core import maximum_path_c def maximum_path(neg_cent, mask): """Cython...
Train 的vits_prepare.py 运行错误：IndexError: Replacement index 2 out of range for positional args tuple
**我按README.md 来操作，如下训练有错误，请问需要怎么处理？** ### Train download baker data: https://www.data-baker.com/data/index/TNtts/ change sample rate of waves to 16kHz, and put waves to ./data/waves put 000001-010000.txt to ./data/000001-010000.txt > python vits_prepare.py -c ./configs/bert_vits.json ###...
您好，请教一下，我的音频大概平均时长是4s左右，有25%的音频在5s 以上，最长10s，这里的segment_size设置需要变大吗？segment_size 太大GPU卡卡显存可能不够用，segment_size 在实际训练是在decoder 部分，只选取一段进行训练吗？这种对长音频的训练为了充分利用数据，需要前提先做一下截取到一个时长范围吗？
语速问题
首先感谢开源，合成效果很棒。 我尝试模型finetune，发现合成的音频总是会比原始语速偏慢，即便是集内的数据。 后来发现这个 https://github.com/PlayVoice/vits_chinese/blob/5b662006ff016f749e6c76a15b4e8e8210a4e1cf/models.py#L562 取ceil的操作可能是原因。但是取floor又会太快。 针对这个问题是否有优化建议呢？
