speech-recognition

JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.

A small speech recognizer

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

OpenAI Whisper ASR Webservice API

Whisper & Faster-Whisper standalone executables for those who don't want to bother with Python.

Open source, local, and self-hosted Amazon Echo/Google Home competitive Voice Assistant alternative

Transcribe any audio to text, translate and edit subtitles 100% locally with a web UI. Powered by whisper models!

Lingvo

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.

A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents

🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks

On-device, real-time multimodal AI with features similar to GPT-Live

Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.

中文语音识别; Mandarin Automatic Speech Recognition;

Open-Source Large Vocabulary Continuous Speech Recognition Engine

A curated list of awesome Speaker Diarization papers, libraries, datasets, and other resources.

The Self-Coding System for Your App — Alan AI SDK for iOS

The Self-Coding System for Your App — Alan AI SDK for Android

Cross-Platform, GPU Accelerated Whisper 🏎️

Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, LicheePi4A etc.

The Self-Coding System for Your App — Alan AI SDK for Flutter

The Self-Coding System for Your App — Alan AI SDK for Ionic

Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.

OBS plugin for local speech recognition and captioning using AI

Amica is an open source interface for interactive communication with 3D characters with voice synthesis and speech recognition.

Custom nodes that extend the capabilities of Comfyui

SALMONN family: A suite of advanced multi-modal LLMs

Open-source LLM-based ASR model family for Chinese, dialect, accent, and multilingual speech, with FunASR, vLLM, streaming, and llama.cpp runtimes.

Unified-Modal Speech-Text Pre-Training for Spoken Language Processing