AI Rank
EN
← 开源
PlayVoice

vits_chinese

Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!

ModelsLanguage-specific modelsAudio/Speech modelsPython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
1.23k
Star
172
Fork
+1
本周
7
贡献者
创建于 2021-09-27 · 更新于 2026-10-11 · 今日第 11047 名
主要开发者
MaxMax2016Kalyanimhalasaakshii12

PlayVoice/vits_chinese 排名第 11,047，有 1,230 个星标。

同类别比较

PlayVoice/vits_chinese 排名第 11,047，此处有 8 个同类条目；Tencent-Hunyuan/HunyuanCustom 排名第 11,048。

同类别比较
名称排名指标
alibaba/Tora10,993
语言:
Python
星标数:
1,243
分叉数:
61
简介:
[CVPR'25]Tora: Trajectory-oriented Diffusion Transformer for Video Generation
declare-lab/tango11,004
语言:
Python
星标数:
1,241
分叉数:
104
简介:
A family of diffusion models for text-to-audio generation.
ElectricAlexis/NotaGen11,016
语言:
Python
星标数:
1,237
分叉数:
139
简介:
NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms
bytedance/USO11,019
语言:
Python
星标数:
1,237
分叉数:
77
简介:
[CVPR 2026] 🔥🔥 Official Repo of USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning
Tencent-Hunyuan/HunyuanCustom11,048
语言:
Python
星标数:
1,230
分叉数:
110
简介:
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
qubvel/classification_models11,051
语言:
Python
星标数:
1,230
分叉数:
307
简介:
Classification models trained on ImageNet. Keras.
MoonshotAI/Kimi-VL11,064
星标数:
1,227
分叉数:
97
简介:
Kimi-VL: Mixture-of-Experts Vision-Language Model for Multimodal Reasoning, Long-Context Understanding, and Strong Agent Capabilities
bheinzerling/bpemb11,067
语言:
Python
星标数:
1,227
分叉数:
100
简介:
Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)
关键参数与规格
关键参数与规格
参数值
语言Python
类别Models
子类别Language-specific models,Audio/Speech models
关键词Text-to-speech
星标数1,230
分叉数172
贡献者7
创建日期2021-09-27
更新日期2026-10-11
1 天星标数0
7 天星标数1
排名11,047
上次排名11,000
排名变化-47
7 天星标排名10,042
上次 7 天星标排名10,082
7 天星标排名变化40
总星标排名9,498
上次总星标排名9,490
总星标排名变化-8
国家China
README 摘录

vits实现的中文TTS this is the copy of VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech Espnet连接：github. com/espnet/espnet/tree/master/espnet2/gan_tts/vits coqui-ai/TTS连接：github. com/coqui-ai/TTS/tree/main/recipes/ljspeech/vits_tts base on: 如果有侵权行为，请联系我，我将删除项目 If there is infringement, please contact

me and I will delete the item 基于VITS 实现 16K baker TTS 的流程记录 pip install -r requirements. json -m baker_base 两张1080卡，训练两天，基本可以使用了 测试 python vits_strings.

常见问题

记录了多少星标和分叉？

PlayVoice/vits_chinese 有 1,230 个星标和 172 个分叉。

仓库排名是多少？

PlayVoice/vits_chinese 排名第 11,047。

记录的语言和类别是什么？

PlayVoice/vits_chinese 有 1,230 个星标，语言为 Python，类别为 Models。

哪个仓库排名最接近？

PlayVoice/vits_chinese 与 Tencent-Hunyuan/HunyuanCustom 比较，后者排名第 11,048，有 1,230 个星标。

README

vits实现的中文TTS

this is the copy of https://github.com/jaywalnut310/vits

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

Espnet连接：github.com/espnet/espnet/tree/master/espnet2/gan_tts/vits

coqui-ai/TTS连接：github.com/coqui-ai/TTS/tree/main/recipes/ljspeech/vits_tts

base on:https://github.com/lutianxiong/vits_chinese

如果有侵权行为，请联系我，我将删除项目

If there is infringement, please contact me and I will delete the item

基于VITS 实现 16K baker TTS 的流程记录

pip install -r requirements.txt

cd monotonic_align

python setup.py build_ext --inplace

将16K标贝音频拷贝到./baker_waves/，启动训练

python train.py -c configs/baker_base.json -m baker_base

两张1080卡，训练两天，基本可以使用了

测试

python vits_strings.py

排名相邻
同类项目