zixiiu / vits
VITS implementation of Japanese, Chinese, Korean, Sanskrit and Thai
☆26Updated last year
Alternatives and similar repositories for vits:
Users that are interested in vits are comparing it to the libraries listed below
- 基于PyTorch的VITS-BigVGAN的tts中文模型,加入韵律预测模型。☆194Updated 2 years ago
- vits chinese, tts chinese, tts mandarin 史上训练最简单,音质最好的语音合成系统☆211Updated 3 years ago
- 基于标贝数据继续训练,同时对原本的FastSpeech2模型做了改进,引入了韵律表征以及韵律预测模块,使中文发音更生动且富有节奏☆261Updated last year
- 语音数据集制作标记工具☆133Updated 2 years ago
- VITS for Mandarin. Support Windows and Linux, low-end and high-end hardwares☆110Updated last year
- application of vits on mandarin tts☆122Updated last year
- 一个快速制作语音数据集的可视化工具☆194Updated last year
- How to use our public wav2vec2 dimensional emotion model☆494Updated last year
- A voiceprint recognition classifier for audio dataset☆99Updated last year
- GPT-SoVITS2☆214Updated 8 months ago
- Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!☆1,183Updated last year
- ☆48Updated last year
- SubFix: Efficient Web-Based Audio Subtitle Editing and Multilingual Automatic Annotation Tool.☆203Updated last year
- BertVITS2前端界面☆300Updated last year
- Simple data labeling script with funasr inside. 使用阿里fanasr进行VITS训练数据标注☆78Updated last year
- HuBERT content encoders for: A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion☆352Updated 6 months ago
- Documentation for Bert-VITS2☆22Updated last year
- VITS implementation of Japanese, Chinese, Korean, Sanskrit and Thai☆924Updated last year
- vits2 backbone with bert☆338Updated last year
- A live2D chatbot Demo build with python and js.☆72Updated last year
- 无需情感标注的情感可控语音合成模型,基于VITS☆1,377Updated 2 years ago
- ☆444Updated 2 months ago
- Fine-Tuning your VITS model using a pre-trained model☆556Updated last year
- vits2 backbone with bert☆85Updated last year
- VC Without Retrain!☆118Updated 11 months ago
- Preprocess Audio for training☆331Updated last month
- ☆278Updated 10 months ago
- a TTS demo for training new characters.☆460Updated last year
- ☆378Updated 2 years ago
- Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform☆444Updated 2 years ago