KevinWang676 / VITS2-Chinese
VITS2 for Chinese speech | 最新VITS2中文语音合成
☆131Updated last year
Alternatives and similar repositories for VITS2-Chinese:
Users that are interested in VITS2-Chinese are comparing it to the libraries listed below
- SubFix: Efficient Web-Based Audio Subtitle Editing and Multilingual Automatic Annotation Tool.☆200Updated last year
- Bert-vits2转写和标注独立整合Webui,整合阿里FunAsr,必剪Asr以及Whisper大模型☆170Updated 7 months ago
- 基于中文文本情绪分析自动切换参考音频的 GPT-SoVITS 推理 Demo☆93Updated 11 months ago
- Transform any person's voice into thousands of different voices (voice converter)☆6Updated last year
- 一个快速制作语音数据集的可视化工具☆193Updated 11 months ago
- vits2 backbone with bert☆84Updated last year
- 将音频或视频中的中文语音识别并导出为srt字幕,基于魔塔社区Paraformer模型☆102Updated 7 months ago
- Bert-vits2-V2.3 训练和推理☆45Updated 11 months ago
- ☆46Updated last year
- GPT-SoVITS 参考音频推理效果批量试听☆49Updated 11 months ago
- video to video translation with voice clone and lip synchronization|带有语音克隆和口型同步的视频翻译,支持中英互换☆123Updated 10 months ago
- 基于OpenVoice和Melotts整合的中文版webui,添加resemble_enhance音频增强功能☆89Updated 10 months ago
- ChatTTS HTTP API☆52Updated 8 months ago
- 10000 chatTTS voices !chatTTS 音色库,再也不为音色抽卡烦恼啦。这是我第一个项目,熬夜龟速生产10000条音色并上传Github,给点鼓励呗哈!主域名:https://www.TTSlist.com 备用:http://ttslist.aiqb…☆155Updated 7 months ago
- Bert-VITS2 onnx推理版本☆40Updated 10 months ago
- 一个简单的音频降噪工具,提高web UI界面和api接口☆19Updated 3 months ago
- 阿里SenseVoice的fastpi封装,采用onnx发布,体积更小,附带量化模型,支持GPU。支持从URL文件进行语音识别。☆61Updated 6 months ago
- ☆118Updated 9 months ago
- ☆42Updated last year
- 语音数据集制作标记工具☆133Updated 2 years ago
- SenseVoice-python: A enterprise-grade open source multi-language asr system from funasr opensource with onnxruntime☆83Updated 5 months ago
- ☆67Updated last year
- ☆272Updated 9 months ago
- Documentation for Bert-VITS2☆22Updated last year
- Simple data labeling script with funasr inside. 使用阿里fanasr进行VITS训练数据标注☆77Updated last year
- 基于GPT-SoVITS的视频剪辑快捷配音工具☆143Updated 11 months ago
- make your Speaker talking as Native style with own voice!☆251Updated last year
- Bert-VITS2项目bug多且教程不友好。本proj尽可能修复了Bert-vits2项目的bug,并且可一键启动训练。仅需50条目标说话人语音,获得稳定、快速的TTS模型。☆49Updated 5 months ago
- Split audio using the .srt file, clean up annotations, then merge and package into a format suitable for bert-vits2 in a standard manner.…☆46Updated 8 months ago
- 洛曦 数字人视频播放器,带HTTP API,使用gradio api对接Easy-Wav2Lip、Sadtalker、GeneFacePlusPlus、MuseTalk,也可以用于播放本地视频☆163Updated 4 months ago