Speech Recognition Models

Models that transcribe spoken audio into text (ASR / speech-to-text).

Top-10 combined DL 30D
65.1M
Tasks directory position
See all tasks
Growth history
Accumulating
Last refresh
Aug 24, 2026

Trending now

#ModelDL 30D7D
1speaker-diarization-community-1pyannote5.3M
2speaker-diarization-3.1pyannote9.9M
3SraVaani-1.0ARTPARK-IISc4,135
4whisper-large-v3openai4.6M
5whisper.cppggerganov0
6Qwen3-ASR-1.7BQwen4.6M
7CN-MultiDialect-ASRASLP-lab335
8whisper-large-v3-turboopenai7.7M
9nemotron-3.5-asr-streaming-0.6bnvidia1M
10parakeet-tdt-0.6b-v3nvidia724.7K

Most downloaded

New & notable

Published within the last 90 days with meaningful traction.

ModelDL 30D7D gained
nemotron-3.5-asr-streaming-0.6b-ggufhandy-computer1.9M
Voxtral-Mini-4B-Realtime-2602-ggufhandy-computer422.1K
Qwen3-ASR-1.7B-hfQwen157.2K
Voxtral-Small-24B-2507-ggufhandy-computer151.5K
Qwen3-ASR-0.6B-hfQwen106.3K
GigaAM-Multilingualai-sage62K
kazakh-whisper-large-v3-turboshyngys87957.1K
cohere-transcribe-arabic-07-2026CohereLabs53.1K
Breeze-ASR-25-ggufhandy-computer39K
Voxtral-Mini-3B-2507-ggufhandy-computer35.9K
Speech Recognition Models — Most Downloaded & Trending | OpenModelStats