YoMio-Tech-Inc / GPT-SoVITS2Links
GPT-SoVITS2
☆224Updated last year
Alternatives and similar repositories for GPT-SoVITS2
Users that are interested in GPT-SoVITS2 are comparing it to the libraries listed below
Sorting:
- ☆289Updated last year
- Preprocess Audio for training☆359Updated 4 months ago
- VC Without Retrain!☆127Updated last year
- text to speech using autoregressive transformer and VITS☆243Updated last year
- ☆146Updated 5 months ago
- A cli tool for split vocal timbre.☆245Updated 5 months ago
- Bert-VITS2 onnx推理版本☆42Updated last year
- 基于PyTorch的VITS-BigVGAN的tts中文模型,加入韵律预测模型。☆194Updated 2 years ago
- SubFix: Efficient Web-Based Audio Subtitle Editing and Multilingual Automatic Annotation Tool.☆206Updated last year
- F5-TTS 推理加速,速度提升约4倍 !☆102Updated 6 months ago
- ☆212Updated 2 years ago
- A collection of neural vocoders suitable for singing voice synthesis tasks.☆128Updated 4 months ago
- Added vLLM support to IndexTTS for faster inference.☆348Updated 2 weeks ago
- 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☆181Updated last year
- Simple data labeling script with funasr inside. 使用阿里fanasr进行VITS训练数据 标注☆80Updated last year
- 一个快速制作语音数据集的可视化工具☆192Updated last year
- Bert-vits2-V2.3 训练和推理☆46Updated last year
- Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform☆457Updated 2 years ago
- 重构GPT-SOVITS的项目,重写了部分代码,优化了webui的使用以及增加了api调用☆28Updated 7 months ago
- BertVITS2前端界面☆302Updated last year
- Unoffical implementation of Megatts2☆286Updated last year
- 基于达摩院视频切割技术的视频转换为短音频的vits数据集生成工具 A VITS Dataset Generation Tool for Converting Video to Short Audio Based on Damo Academy Video Cutting T…☆55Updated last year
- ☆456Updated last month
- 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。☆62Updated 4 months ago
- ☆118Updated 3 weeks ago
- Diffusion Singing Voice Conversion based on Grad-TTS from HuaWei☆148Updated last year
- Next-generation TTS model using flow-matching and DiT, inspired by Stable Diffusion 3☆415Updated 10 months ago
- 这个项目是数据预处理。第一步是对获取到的音频做处理,结合Funasr的时间戳去掉空背景音。也包含了喂给BERT前的label☆17Updated 2 months ago
- 使用vllm加速cosyvoice2的推理☆375Updated 3 months ago
- An Open-Sourced LLM-empowered Foundation TTS System☆754Updated 2 months ago