MrXnneHang / auto_labeling_for_BERT_VITS2
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
☆12Updated 2 months ago
Related projects: ⓘ
- ☆98Updated 3 weeks ago
- 数据集自动化制作脚本☆72Updated last year
- ☆24Updated last year
- A collection of neural vocoders suitable for singing voice synthesis tasks.☆92Updated last week
- GPT-SoVITS2☆167Updated last month
- VITS with phoneme-level prosody modeling based on MaskGIT☆71Updated 2 weeks ago
- only rmvpe☆17Updated last year
- Diffusion Singing Voice Conversion based on Grad-TTS from HuaWei☆124Updated 10 months ago
- VC Without Retrain!☆91Updated 4 months ago
- PITS: Variational Pitch Inference for End-to-end Pitch-controllable TTS without External Pitch Predictor☆17Updated last year
- ☆13Updated 3 months ago
- ☆65Updated 2 weeks ago
- 基 于vits fastspeech2 visinger的tts模型☆23Updated last year
- ☆14Updated 2 months ago
- Sovits5 with RMVPE☆12Updated last year
- ☆92Updated last month
- An Implementation of Singing Voice Conversion Based on Diffsinger☆70Updated last year
- Pipelines and tools to build your own DiffSinger dataset.☆86Updated 5 months ago
- ☆67Updated last year
- Preprocess Audio for training☆223Updated last month
- Bert-VITS2 onnx推理版本☆37Updated 4 months ago
- 基于FreeVC的歌声转换☆21Updated 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…☆49Updated 8 months ago
- ☆13Updated last year
- ☆54Updated 11 months ago
- ☆243Updated 3 months ago
- so-vits-svc rewritten in jax and flax.☆0Updated 3 weeks ago
- text to speech using autoregressive transformer and VITS☆224Updated 5 months ago
- Application of MB-iSTFT-VITS components to vits2_pytorch☆107Updated 2 months 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☆136Updated 2 months ago