automatic speech recognition (ASR) / speech-to-text
High-performance GPGPU inference engine for OpenAI's Whisper automatic speech recognition (ASR) model in C++.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Full-featured ASR toolkit with training/streaming; pick it when you need an all-in-one pipeline in Python rather than low-level Whisper inference.
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Production-oriented ASR toolkit; choose it when you need streaming and deployment tooling in Python.
Production First and Production Ready End-to-End Speech Recognition Toolkit
Reference Python implementation of the same Whisper model; choose it for canonical Python code or model training, not for C++ GPGPU speed.
Robust Speech Recognition via Large-Scale Weak Supervision
Alternative ASR model family; choose it for a different model without C++ GPU engine.
GLM-ASR-Nano: A robust, open-source speech recognition model with 1.5B parameters
Independent STT toolkit with its own models and training; choose it if you don't need Whisper specifically.
🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.
State-of-the-art multilingual ASR model family; choose it for Chinese/dialect support beyond Whisper.
Open-source LLM-based ASR model family for Chinese, dialect, accent, and multilingual speech, with FunASR, vLLM, streaming, and llama.cpp runtimes.
Comprehensive speech toolkit; choose it for extra features like TTS and speaker verification in one Python package.
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
Industrial-grade ASR models for Mandarin and dialects; choose it for those languages over Whisper.
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.
Lightweight multilingual ASR model with emotion recognition; choose it for additional tasks beyond ASR.
Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.
On-device speech AI framework for Apple Silicon; choose it for Apple-native development.
On-device Speech AI for Apple Silicon
MLX and CoreML based speech toolkit for Apple Silicon; choose it for fast on-device ASR in Swift.
AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML
Tiny multi-purpose audio model that also does ASR; choose it when model size matters above all.
[AutoArk] GPA (General Purpose Audio) can do ASR, TTS and voice conversion with one tiny model!
Modern ASR model series with stable multilingual recognition; choose it for latest Qwen ASR quality.
Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Outdated research implementation of transformer ASR; only useful for learning or specific legacy needs.
A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.
Legacy TensorFlow speech recognition code; only useful for historical or educational purposes.
🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks
Old TensorFlow end-to-end ASR implementation; outdated and not production-ready.
End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
Desktop GUI app for subtitle generation; use it as an end-user tool, not a library.
视频转字幕、字幕翻译、AI 配音与声音克隆、字幕烧录——免费开源的一站式桌面工具。基于 Whisper / FunASR 等本地模型离线语音转文字，批量处理 + 全平台 GPU 加速，跨 Windows / macOS / Linux。Free, open-source desktop app to generate, translate, dub & burn video subtitles — local Whisper speech-to-text, AI dubbing & voice cloning, offline, GPU-accelerated.
Desktop app for offline transcription and translation powered by Whisper; end-user tool.
Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
Offline audio/video-to-subtitle tool with GUI/CLI; end-user tool.
Voice Recognition to Text Tool / 一个离线运行的本地音视频转字幕工具，输出json、srt字幕、纯文字格式
Android keyboard app using ASR; end-user mobile application.
说点啥（BiBi Keyboard）:一个基于 Kotlin 的 Android 平台的 LLM 与 ASR 语音输入法键盘应用 An LLM ASR voice input method keyboard application for the Android platform based on Kotlin
Demo app for Vosk on Android; use it as a reference or end-user demo, not a library.
Offline speech recognition for Android with Vosk library.
Voice assistant application built on faster-whisper; end-user realtime assistant, not a library.
Real-time voice assistant — WebRTC streaming, faster-whisper ASR, local LLM, Vui Nano (300M) TTS. OpenAI Realtime API compatible. Voice cloning, barge-in, ~9× realtime on a 4090. Apache 2.0.
These projects were analysed and named Whisper among their alternatives. The relationship is not symmetric — how Whisper rates them is a separate judgement, made when Whisper is analysed in its own right.
calls Whisper “choose for high-performance C++ Whisper inference without Python.”
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
calls Whisper “choose for high-performance GPU inference of Whisper models in C++ without Python or a full toolkit.”
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)