Leaderboard alternatives for AI agents.

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

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

A talking LLM that runs on your own computer without needing the internet.

Foundational Model for Speech Recognition Tasks

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

Build real time speech2text web apps using OpenAI's Whisper https://openai.com/blog/whisper/

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。

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

:speech_balloon: SpeechPy - A Library for Speech Processing and Recognition: http://speechpy.readthedocs.io/en/latest/

Stephanie is an open-source platform built specifically for voice-controlled applications as well as to automate daily tasks imitating much of an virtual assistant's work.

Adapt Intent Parser

Project that allows one to use a microphone with OpenAI whisper.

Chinese text normalization for speech processing

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