MrXnneHang / auto_labeling_for_BERT_VITS2Links
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
☆16Updated 5 months ago
Alternatives and similar repositories for auto_labeling_for_BERT_VITS2
Users that are interested in auto_labeling_for_BERT_VITS2 are comparing it to the libraries listed below
Sorting:
- GPT-SoVITS2☆227Updated last year
- A cli tool for split vocal timbre.☆260Updated 8 months ago
- ☆297Updated last year
- ☆152Updated 9 months ago
- 基于PyTorch的VITS-BigVGAN的tts中文模型,加入韵律预测模型。☆196Updated 3 years ago
- VC Without Retrain!☆128Updated last year
- 一个快速制作语音数据集的可视化工具☆194Updated last year
- ☆467Updated 4 months ago
- text to speech using autoregressive transformer and VITS☆246Updated last year
- Preprocess Audio for training☆366Updated last week
- Bert-VITS2 onnx推理版本☆43Updated 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☆184Updated last year
- 数据集自动化制作脚本☆72Updated 2 years ago
- A lightweight tool that efficiently isolates target speaker data from your datasets.☆19Updated 11 months ago
- A collection of neural vocoders suitable for singing voice synthesis tasks.☆138Updated this week
- vits2 backbone with bert☆340Updated last year
- SubFix: Efficient Web-Based Audio Subtitle Editing and Multilingual Automatic Annotation Tool.☆209Updated last year
- ☆220Updated 2 years ago
- Simple data labeling script with funasr inside. 使用阿里fanasr进行VITS训练数据标注☆80Updated 2 years ago
- Diffusion Singing Voice Conversion based on Grad-TTS from HuaWei☆159Updated 2 years ago
- Bert-vits2-V2.3 训练和推理☆49Updated last year
- application of vits on mandarin tts☆120Updated 2 years ago
- Pipelines and tools to build your own DiffSinger dataset.☆121Updated 7 months ago
- VITS for Mandarin. Support Windows and Linux, low-end and high-end hardwares☆111Updated 2 years ago
- Ultimate Vocal Remover CLI☆151Updated 9 months ago
- Sovits5 with RMVPE☆14Updated 2 years ago
- BertVITS2前端界面☆301Updated last year
- Vits Japanese with Whisper as data processor (you can train your VITS even you only have audios)☆162Updated 2 years ago
- Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform☆464Updated 2 years ago
- 音频响度统一,音量归一化处理☆12Updated last year