yeyupiaoling / VITS-Pytorch
本项目是基于Pytorch的语音合成项目，使用的是VITS，VITS是一种语音合成方法，这种时端到端的模型使用起来非常简单，不需要文本对齐等太复杂的流程，直接一键训练和生成，大大降低了学习门槛。
☆38Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for VITS-Pytorch
- 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☆247Updated last year
- Bert-VITS2 onnx推理版本☆40Updated 6 months ago
- 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。☆28Updated last month
- Unoffical implementation of Megatts2☆264Updated 7 months ago
- A enterprise-grade Voice Activity Detector from modelscope and funasr.☆61Updated last year
- Pseudo Streaming SenseVoice with Hotwords☆78Updated last week
- 基于PyTorch的VITS-BigVGAN的tts中文模型，加入韵律预测模型。☆193Updated 2 years ago
- GPT-SoVITS2☆181Updated 3 months ago
- Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English☆71Updated this week
- ☆80Updated last year
- TTS appalication based on modelscope KAN-TTS☆43Updated 7 months ago
- VC Without Retrain!☆102Updated 6 months ago
- Grapheme-to-Phoneme lexicons for Chinese dialects☆66Updated last year
- ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).☆52Updated this week
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆371Updated 5 months ago
- text to speech using autoregressive transformer and VITS☆227Updated 7 months ago
- ☆166Updated last month
- A enterprise-grade Chinese-English code switch punctuator from funasr.☆18Updated 6 months ago
- ☆19Updated 5 months ago
- 基于 g2pW 提升 pypinyin 的准确性☆78Updated last year
- Huawei Grad-TTS for Chinese☆45Updated last year
- 基于FunASR实现语音识别，包含常规版和ONNX版(推荐)。☆24Updated last month
- 端到端语音唤醒工具箱，从模型训练到模型推理。☆73Updated 2 months ago
- ☆36Updated 3 months ago
- Forced Alignment-MFA☆33Updated 2 years ago
- 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…☆52Updated 9 months ago
- Sovits5 with RMVPE☆14Updated last year
- 百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，时延低至800ms，低配置也可运行，支持打断☆35Updated last month