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

Authority projects

Projects with the strongest long-term signal in Automatic Speech Recognition, ranked by total stars, likes, or runs on their primary platform.

whisperx

Transcribe audio files quickly and accurately with word-level timestamps and speaker diarization.

Replicate
9.1Mruns

whisper-diarization

Fast audio transcription with speaker diarization and word level timestamps.

Replicate
9.1Mruns

whisperx-a40-large

Fast and accurate speech recognition for large audio files with word-level timestamps and speaker diarization.

Replicate
3.7Mruns

whisper-diarization-advanced

Replicate

Replicate
598.2Kruns

scribe-v2

Transcribe speech to text with advanced features like speaker diarization and audio event tagging.

Replicate
432.8Kruns

whisperx-subtitles-replicate

Replicate

Replicate
157.5Kruns

openai/whisper-large-v3

Automatic speech recognition model for transcribing audio files and recognizing spoken language.

Hugging Face Model
6.3Klikes

quill

GitHub

GitHub
3.7Kstars

grok-speech-to-text

Transcribe audio to text with advanced features like word-level timestamps and speaker diarization.

Replicate
2.3Kruns

openless

Speak and generate polished text at your cursor in any app.

GitHub
1.3Kstars

qwenasr

Speech recognition and alignment model providing word-level timestamps for transcription.

Replicate
1.3Kruns

Qwen3-ASR

Advanced speech recognition models for multilingual support and language detection.

GitHub
1.2Kstars

Hidden gems

Smaller projects with unusually strong momentum. We look for lower total metrics plus positive 7-day growth.

murmur

GitHub

GitHub
93stars
927d

grok-speech-to-text

Transcribe audio to text with advanced features like word-level timestamps and speaker diarization.

Replicate
2.3Kruns
4067d

parakeet.cpp

Fast and efficient speech recognition on CPU and GPU.

GitHub
206stars
2067d

MiMo-V2.5-ASR

Accurate speech recognition across languages and acoustic scenarios.

GitHub
138stars
1387d

CohereLabs/Cohere-Transcribe-WebGPU

Transcribe audio into text instantly in your browser.

Hugging Face Space
64likes
357d

andito/parakeet-v3-streaming

Transcribe speech instantly with real-time results and smart streaming.

Hugging Face Space
74likes
367d

CohereLabs/cohere-transcribe-03-2026

Transcribe audio to text in multiple languages with this speech recognition model

Hugging Face Space
89likes
427d

Qwen/Qwen3-ASR

Convert speech to text with accurate word-level timestamps and support for 30+ languages.

Hugging Face Space
89likes
417d

SoulX-Transcriber

Transcribe multi-speaker conversations with high accuracy and coherence.

GitHub
196stars
1027d

QwenASRMiniTool

Recognize speech in real-time or from audio files and generate subtitles with ease.

GitHub
199stars
797d

yapsnap

Transcribe video or audio into text with one command.

GitHub
237stars
1077d

FireRedASR2S

Advanced speech recognition system for multiple languages and dialects.

GitHub
222stars
887d