facebook/omniASR-LLM-7B
Automatic Speech Recognition • Updated • 36
asr models
-
-
mistralai/Voxtral-Small-24B-2507
Audio-Text-to-Text • 24B • Updated • 249k • 523 -
mistralai/Voxtral-Mini-4B-Realtime-2602
Automatic Speech Recognition • 4B • Updated • 2.33M • 952 -
Qwen/Qwen3-ASR-0.6B
Automatic Speech Recognition • 0.9B • Updated • 2.51M • • 342 -
nvidia/parakeet-tdt-0.6b-v3
Automatic Speech Recognition • 0.6B • Updated • 719k • • 1.07k -
facebook/omniASR-CTC-1B
Automatic Speech Recognition • Updated • 9 -
facebook/omniASR-CTC-300M
Automatic Speech Recognition • Updated • 14 -
openai/whisper-large-v3-turbo
Automatic Speech Recognition • 0.8B • Updated • 7.34M • • 3.27k -
nvidia/canary-1b-v2
Automatic Speech Recognition • Updated • 12.4k • 410 -
Granary: Speech Recognition and Translation Dataset in 25 European Languages
Paper • 2505.13404 • Published • 4 -
Qwen/Qwen3-ASR-1.7B
Automatic Speech Recognition • 2B • Updated • 4.54M • • 1.04k -
ibm-granite/granite-speech-3.3-8b
Automatic Speech Recognition • 9B • Updated • 46.4k • 171 -
nvidia/canary-qwen-2.5b
Automatic Speech Recognition • 3B • Updated • 25.3k • 455 -
facebook/omniASR-LLM-300M
Automatic Speech Recognition • Updated • 6 -
ai4bharat/indic-conformer-600m-multilingual
Automatic Speech Recognition • Updated • 68.2k • 119 -
sarvamai/shuka-1
Audio-Text-to-Text • 9B • Updated • 245 • 94 -
google/medasr
Automatic Speech Recognition • 0.1B • Updated • 126k • 359 -
google/gemma-4-E2B
Any-to-Any • 5B • Updated • 80.6k • 448 -
google/gemma-4-E2B-it
Any-to-Any • 5B • Updated • 3.42M • 919 -
google/gemma-4-E4B
Any-to-Any • 8B • Updated • 405k • 400 -
google/gemma-4-E4B-it
Any-to-Any • 8B • Updated • 5.01M • 1.51k -
nvidia/parakeet-tdt-0.6b-v2
Automatic Speech Recognition • Updated • 279k • 1.54k -
nvidia/nemotron-3.5-asr-streaming-0.6b
Automatic Speech Recognition • 0.6B • Updated • 922k • • 1.07k -
ibm-granite/granite-speech-4.1-2b
Automatic Speech Recognition • 2B • Updated • 248k • 157 -
nvidia/stt_en_fastconformer_ctc_large
Automatic Speech Recognition • Updated • 1.82k • 20 -
ibm-granite/granite-speech-3.3-2b
Automatic Speech Recognition • 3B • Updated • 234k • 55 -
hyperneuronAILabs/quipus-0.6-speechv2
Text-to-Speech • 0.6B • Updated • 630 • 1