Topic Hub
Best Automatic Speech Recognition Open Source Projects
This hub collects the best open source projects in Automatic Speech Recognition and ranks them by both momentum and authority.
Data window: Last 7 days (with 24h tie-breakers for Trending now)
Last updated: Sep 18, 2026
Projects
49
GitHub stars
13.8K
Hugging Face likes
10.7K
Replicate runs
23.2M
Trending now
Fastest-growing projects in Automatic Speech Recognition over the last 7 days, with 24h change as a tie-breaker.
whisperx
Transcribe audio files quickly and accurately with word-level timestamps and speaker diarization.
whisper-diarization
Fast audio transcription with speaker diarization and word level timestamps.
scribe-v2
Transcribe speech to text with advanced features like speaker diarization and audio event tagging.
whisperx-a40-large
Fast and accurate speech recognition for large audio files with word-level timestamps and speaker diarization.
TypeNo
Simple voice input app for macOS with local speech recognition and privacy focus.
grok-speech-to-text
Transcribe audio to text with advanced features like word-level timestamps and speaker diarization.
Mega-ASR
Robust speech recognition model for real-world scenarios with up to 30% gains over state-of-the-art models.
qwen-asr
Transcribe audio files and streams to text in real-time with high accuracy.
Hidden gems
Smaller projects with unusually strong momentum. We look for lower total metrics plus positive 7-day growth.
grok-speech-to-text
Transcribe audio to text with advanced features like word-level timestamps and speaker diarization.
MiMo-V2.5-ASR
Accurate speech recognition across languages and acoustic scenarios.
CohereLabs/Cohere-Transcribe-WebGPU
Transcribe audio into text instantly in your browser.
andito/parakeet-v3-streaming
Transcribe speech instantly with real-time results and smart streaming.
CohereLabs/cohere-transcribe-03-2026
Transcribe audio to text in multiple languages with this speech recognition model
Qwen/Qwen3-ASR
Convert speech to text with accurate word-level timestamps and support for 30+ languages.
SoulX-Transcriber
Transcribe multi-speaker conversations with high accuracy and coherence.
QwenASRMiniTool
Recognize speech in real-time or from audio files and generate subtitles with ease.
FireRedASR2S
Advanced speech recognition system for multiple languages and dialects.