1,054 models · refreshed nightly

Automatic speech recognition models

Every model in the catalog with its licence, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.

All text-generation 410 text-to-image 153 ASR 92 image-text-to-text 89 sentence-similarity 61 feature-extraction 47 translation 47 text-classification 42 image-classification 34 token-classification 27 text-to-speech 12 audio-classification 11 object-detection 11 summarization 9 image-segmentation 9

Any RTX 3060 · 12 GB RTX 4070 · 16 GB RTX 4090 · 24 GB 2 × 24 GB Mac M3 · 24 GB Mac M4 Max · 64 GB

92 models

#	Model	Params	Context	Commercial use	30d	Min VRAM
51	faster-whisper-large-v3 Systran · ASR	—	—	✓ mit	1.0 M	—
52	wav2vec2-xlsr-nepali gagan3012 · ASR	—	—	✓ apache-2.0	993 K	—
53	wav2vec2-large-xlsr-korean kresnik · ASR	320 M	—	✓ apache-2.0	983 K	from 1.9 GB
54	cohere-transcribe-03-2026-gguf handy-computer · ASR	—	—	✓ apache-2.0	963 K	from 2.2 GB
55	wav2vec2-xls-r-300m-ftspeech saattrupdan · ASR	320 M	—	other	949 K	from 1.9 GB
56	wav2vec2-large-xlsr-mvc-swahili eddiegulay · ASR	320 M	—	✓ apache-2.0	845 K	from 1.9 GB
57	whisper-tiny.en Xenova · ASR	—	—	✓ apache-2.0	805 K	—
58	faster-whisper-small.en Systran · ASR	—	—	✓ mit	769 K	—
59	faster-whisper-medium Systran · ASR	—	—	✓ mit	761 K	—
60	nemotron-3.5-asr-streaming-0.6b nvidia · ASR	640 M	—	other	752 K	from 1.4 GB
61	wav2vec2-large-xlsr-catala softcatala · ASR	—	—	✓ apache-2.0	747 K	—
62	VibeVoice-ASR microsoft · ASR	8.7 B	—	✓ mit	740 K	from 20.9 GB
63	parakeet-ctc-1.1b nvidia · ASR	1.1 B	—	✓ cc-by-4.0	721 K	from 2.0 GB
64	wav2vec2-large-xlsr-malayalam gvs · ASR	—	—	✓ apache-2.0	649 K	—
65	wav2vec2-large-xlsr-53-arabic elgeish · ASR	—	—	✓ apache-2.0	623 K	—
66	Qwen3-ASR-0.6B Qwen · ASR	940 M	—	✓ apache-2.0	603 K	from 2.7 GB
67	parakeet-tdt-0.6b-v3 nvidia · ASR	630 M	—	✓ cc-by-4.0	586 K	from 1.4 GB
68	parakeet-tdt-0.6b-v3-gguf handy-computer · ASR	—	—	✓ cc-by-4.0	580 K	from 1.0 GB
69	wav2vec2-large-xlsr-lithuanian m3hrdadfi · ASR	—	—	✓ apache-2.0	572 K	—
70	wav2vec2-large-xls-r-300m-welsh infinitejoy · ASR	300 M	—	✓ apache-2.0	567 K	from 1.2 GB
71	wav2vec2-xls-r-300m-cv7-turkish mpoyraz · ASR	300 M	—	✓ cc-by-4.0	558 K	from 1.2 GB
72	whisper-bemba-stt AbelZimba · ASR	240 M	—	unknown	535 K	from 1.6 GB
73	whisper-medium-gguf handy-computer · ASR	—	—	✓ apache-2.0	533 K	from 1.1 GB
74	faster-whisper-base.en Systran · ASR	—	—	✓ mit	526 K	—
75	wav2vec2-large-xlsr-53-estonian anton-l · ASR	—	—	✓ apache-2.0	523 K	—
76	distil-large-v3 distil-whisper · ASR	760 M	—	✓ mit	523 K	from 5.6 GB
77	wav2vec2-xls-r-300m-sk-cv8 comodoro · ASR	300 M	—	✓ apache-2.0	505 K	from 1.2 GB
78	wav2vec2-large-xlsr-japanese-hiragana vumichien · ASR	320 M	—	✓ apache-2.0	472 K	from 1.9 GB
79	faster-whisper-tiny.en Systran · ASR	—	—	✓ mit	469 K	—
80	wav2vec2-large-xls-r-300m-sinhala-low-LR-part1 SpideyDLK · ASR	320 M	—	unknown	469 K	from 1.9 GB
81	wav2vec2-large-xlsr-53-basque stefan-it · ASR	320 M	—	✓ apache-2.0	468 K	from 1.9 GB
82	wav2vec2-xlsr-khmer gagan3012 · ASR	—	—	✓ apache-2.0	458 K	—
83	vakyansh-wav2vec2-sanskrit-sam-60 Harveenchadha · ASR	—	—	unknown	449 K	—
84	wav2vec2-large-xlsr-kn amoghsgopadi · ASR	—	—	✓ apache-2.0	447 K	—
85	Voxtral-Mini-4B-Realtime-2602-gguf handy-computer · ASR	—	—	✓ apache-2.0	442 K	from 3.6 GB
86	indic-conformer-600m-multilingual ai4bharat · ASR · gated	600 M	—	✓ mit	436 K	from 1.9 GB
87	whisper-large-v3-turbo-german primeline · ASR	810 M	—	✓ apache-2.0	428 K	from 2.4 GB
88	wav2vec2-large-mms-1b-azerbaijani-common_voice15.0 nijatzeynalov · ASR	960 M	—	✗ cc-by-nc-4.0	427 K	from 4.9 GB
89	wav2vec2-large-xls-r-300m-bg-d2 DrishtiSharma · ASR	300 M	—	✓ apache-2.0	419 K	from 1.2 GB
90	nemotron-speech-streaming-en-0.6b nvidia · ASR	618 M	—	other	417 K	from 1.4 GB
91	Qwen3-ForcedAligner-0.6B Qwen · ASR	920 M	—	✓ apache-2.0	417 K	from 2.7 GB
92	wav2vec2-large-xlsr-53-slovenian anton-l · ASR	—	—	✓ apache-2.0	402 K	—

VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.