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。
☆45Updated 7 months ago
Alternatives and similar repositories for VITS-Pytorch:
Users that are interested in VITS-Pytorch are comparing it to the libraries listed below
- 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☆259Updated last year
- 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。☆52Updated 3 weeks ago
- 使用vllm加速cosyvoice2的推理☆127Updated last week
- Unoffical implementation of Megatts2☆279Updated 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
- Bert-VITS2 onnx推理版本☆41Updated 11 months ago
- KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-…☆504Updated last year
- ☆193Updated 6 months 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☆27Updated 3 months ago
- 本项目使用了EcapaTdnn、ResNetSE、ERes2Net、CAM++等多种先进的声纹识别模型,同时本项目也支持了MelSpectrogram、Spectrogram、MFCC、Fbank等多种数据预处理方法☆260Updated 3 weeks ago
- Forced Alignment-MFA☆38Updated 2 years ago
- 基于Pytorch实现的语音情感识别☆181Updated 3 weeks ago
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆385Updated 10 months ago
- ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).☆64Updated 3 months ago
- Documentation for Bert-VITS2☆22Updated last year
- TTS appalication based on modelscope KAN-TTS☆43Updated 11 months ago
- A enterprise-grade Chinese-English code switch punctuator from funasr.☆22Updated 11 months ago
- The dataset of Speech Recognition☆409Updated 3 months ago
- 端到端语音唤醒工具箱,从模型训练到模型推理。☆109Updated 6 months ago
- 使用python进行语音识别☆147Updated 3 years ago
- This repository is to implement the processes for users have no GUI☆17Updated 11 months ago
- ☆108Updated last year
- GPT-SoVITS2☆214Updated 8 months 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…☆54Updated last year
- Considering the original Wav2Lip was trained on LSR2 and didn't have good performance on Chinese. I preprocessed CMLR Dataset and would t…☆60Updated last year
- FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music gener…☆392Updated last year
- 基于FunASR实现语音识别,包含常规版和ONNX版(推荐)。☆36Updated 5 months ago
- 修复funasr中seaco-paraformer导出onnx后没有时间戳的bug☆19Updated 6 months ago
- 语音数据集制作标记工具☆133Updated 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☆212Updated 3 years ago