MASR alternatives for AI agents.

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

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。

On-device streaming speech-to-text engine powered by deep learning

speech to text benchmark framework

Open source, local, and self-hosted highly optimized language inference server supporting ASR/STT, TTS, and LLM across WebRTC, REST, and WS

Speech-to-text server framework with next-gen Kaldi

An Optimized Speech-to-Text Pipeline for the Whisper Model Supporting Multiple Inference Engine

Optimized Whisper models for streaming and on-device use

Allosaurus is a pretrained universal phone recognizer for more than 2000 languages

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain

Open-Source Toolkit for End-to-End Korean Automatic Speech Recognition leveraging PyTorch and Hydra.

A SOTA Industrial-Grade All-in-One ASR system with ASR, VAD, LID, and Punc modules. FireRedASR2 supports Chinese (Mandarin, 20+ dialects/accents), English, code-switching, and both speech and singing ASR. FireRedVAD supports speech/singing/music in 100+ langs. FireRedLID supports 100+ langs and 20+ zh dialects. FireRedPunc supports zh and en.

Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

📦 快速转化「中文数字」和「阿拉伯数字」～ (最新特性：分数，日期、温度等转化）

SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.