Zhongwen Real Time Voice Cloning
v1.1.4
详见readme
- 原始语音和克隆语音对比样例
链接: https://pan.baidu.com/s/1TQwgzEIxD2VBrVZKCblN1g
提取码: 8ucd
- toolbox
- 合成样例
- 注意
跑提供的模型建议用Griffin-Lim声码器，目前MelGAN和WaveRNN没有完全适配。
代码，包括encoder、synthesizer、vocoder、toolbox模块，包括模型训练的模块和可视化合成语音的模块。
执行脚本需要进入zhrtvc目录操作。
代码相关的说明详见zhrtvc目录下的readme文件。
预训练的模型，包括encoder、synthesizer、vocoder的模型。
预训练的模型在百度网盘下载，下载后解压，替换models文件夹即可。
- 样本模型
链接：https://pan.baidu.com/s/14hmJW7sY5PYYcCFAbqV0Kw
提取码：zl9i
语料样例，包括语音和文本对齐语料，处理好的用于训练synthesizer的数据样例。
可以直接执行synthesizer_preprocess_audio.py和synthesizer_preprocess_embeds.py把samples的语音文本对齐语料转为SV2TTS的用于训练synthesizer的数据。
语料样例在百度网盘下载，下载后解压，替换data文件夹即可。
- 样本数据
链接：https://pan.baidu.com/s/1Q_WUrmb7MW_6zQSPqhX9Vw
提取码：bivr
【AI解决方案交流群】QQ群：925294583
点击链接加入群聊：https://jq.qq.com/?_wv=1027&k=wlQzvT0N
This repository is an implementation of Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis (SV2TTS) with a vocoder that works in real-time. Feel free to check my thesis if you're curious or if you're looking for info I haven't documented yet (don't hesitate to make an issue for that too). Mostly I would recommend giving a quick look to the figures beyond the introduction.
SV2TTS is a three-stage deep learning framework that allows to create a numerical representation of a voice from a few seconds of audio, and to use it to condition a text-to-speech model trained to generalize to new voices.
| URL | Designation | Title | Implementation source |
|---|---|---|---|
| 1806.04558 | SV2TTS | Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis | This repo |
| 1802.08435 | WaveRNN (vocoder) | Efficient Neural Audio Synthesis | fatchord/WaveRNN |
| 1712.05884 | Tacotron 2 (synthesizer) | Natural TTS Synthesis by Conditioning Wavenet on Mel Spectrogram Predictions | Rayhane-mamah/Tacotron-2 |
| 1710.10467 | GE2E (encoder) | Generalized End-To-End Loss for Speaker Verification | This repo |