yeyupiaoling / MASR
Pytorch实现的流式与非流式的自动语音识别框架,同时兼容在线和离线识别,目前支持Conformer、Squeezeformer、DeepSpeech2模型,支持多种数据增强方法。
☆655Updated 2 weeks ago
Alternatives and similar repositories for MASR:
Users that are interested in MASR are comparing it to the libraries listed below
- 基于PaddlePaddle实现端到端中文语音识别,从入门到实战,超简单的入门案例,超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型☆850Updated 2 weeks ago
- 基于PaddlePaddle实现的语音识别,中文语音识别。项目完善,识别效果好。支持Windows,Linux下训练和预测,支持Nvidia Jetson开发板预测。☆724Updated 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 last month
- Production First and Production Ready End-to-End Keyword Spotting Toolkit☆523Updated last month
- 一个执着于让CPU\端侧-Model逼近GPU-Model性能的项目,CPU上的实时率(RTF)小于0.1☆472Updated 3 weeks ago
- This project uses a variety of advanced voiceprint recognition models such as EcapaTdnn, ResNetSE, ERes2Net, CAM++, etc. It is not exclud…☆939Updated last month
- 这是一个用C++实现ASR推理的项目,它依赖很少,安装也很简单,推理速度很快,在树莓派4B等ARM平台也可以流畅的运行。 支持的模型是由Google的Transformer模型中优化而来,数据集是开源wenetspeech(10000+小时)或阿里私有数据集(60000+小…☆504Updated 2 years ago
- The dataset of Speech Recognition☆409Updated 3 months ago
- tacotronV2 + wavernn 实现中文语音合成(Tensorflow + pytorch)☆534Updated last year
- A 10000+ hours dataset for Chinese speech recognition☆523Updated last year
- 中文语音识别; Mandarin Automatic Speech Recognition;☆1,920Updated 8 months ago
- 语音识别理论、论文和PPT☆597Updated 7 months ago
- Automatic Speech Recognition(ASR), Text-To-Speech(TTS) engine. 中英语音识别、多角色语音合成,支持多语言,准确率高☆491Updated 3 months ago
- 使用Tensorflow实现声纹识别☆308Updated 9 months ago
- chinese speech pretrained models☆1,094Updated 7 months ago
- Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training wit…☆997Updated 2 months ago
- Chinese Mandarin tts text-to-speech 中文 (普通话) 语音 合成 , by fastspeech 2 , implemented in pytorch, using waveglow as vocoder, with biaobei …☆472Updated 2 years ago
- SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.☆483Updated this week
- 使用python进行语音识别☆147Updated 3 years ago
- Chinese text normalization for speech processing☆655Updated 2 years ago
- Chinese voice corpus. 中文语音语料,语音更加清晰自然,包含8个开源数据集,3200个说话人,900小时语音,1300万字。☆628Updated 4 years ago
- An Open Source Tools for Speaker Recognition☆613Updated 7 months 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☆259Updated last year
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆385Updated 10 months ago
- An Automatic Speech Recognition Frame ,一个中文语音识别的完整框架, 提供了多个模型☆246Updated 4 years ago
- Text Normalization & Inverse Text Normalization☆561Updated 4 months ago
- 基于Pytorch实现的语音情感识别☆181Updated 3 weeks ago
- 端到端中文语音识别☆87Updated 8 months ago
- The Pytorch implementation of sound classification supports EcapaTdnn, PANNS, TDNN, Res2Net, ResNetSE and other models, as well as a vari…☆468Updated last month
- ☆108Updated last year