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
01	wav2vec2-large-xlsr-53-japanese jonatasgrosman · ASR	—	—	✓ apache-2.0	17.9 M	—
02	whisperkit-coreml argmaxinc · ASR	—	—	✓ mit	11.2 M	—
03	speaker-diarization-3.1 pyannote · ASR · gated	—	—	✓ mit	8.2 M	—
04	whisper-large-v3-turbo openai · ASR	810 M	—	✓ mit	6.8 M	from 2.4 GB
05	wav2vec2-large-xlsr-53-portuguese jonatasgrosman · ASR	—	—	✓ apache-2.0	6.0 M	—
06	speaker-diarization-community-1 pyannote · ASR · gated	—	—	✓ cc-by-4.0	5.3 M	—
07	whisper-large-v3 openai · ASR	1.5 B	—	✓ apache-2.0	4.7 M	from 10.9 GB
08	wav2vec2-large-xlsr-53-russian jonatasgrosman · ASR	—	—	✓ apache-2.0	4.2 M	—
09	wav2vec2-large-xlsr-53-polish jonatasgrosman · ASR	—	—	✓ apache-2.0	3.7 M	—
10	wav2vec2-large-xlsr-53-dutch jonatasgrosman · ASR	—	—	✓ apache-2.0	3.1 M	—
11	wav2vec2-indonesian-javanese-sundanese indonesian-nlp · ASR	—	—	✓ apache-2.0	3.1 M	—
12	whisper-small openai · ASR	240 M	—	✓ apache-2.0	2.9 M	from 1.6 GB
13	wav2vec2-large-xlsr-53-greek jonatasgrosman · ASR	—	—	✓ apache-2.0	2.9 M	—
14	faster-whisper-small Systran · ASR	—	—	✓ mit	2.9 M	—
15	mms-300m-1130-forced-aligner MahmoudAshraf · ASR	320 M	—	✗ cc-by-nc-4.0	2.7 M	from 1.9 GB
16	faster-whisper-tiny Systran · ASR	—	—	✓ mit	2.5 M	—
17	wav2vec2-large-xlsr-53-hungarian jonatasgrosman · ASR	—	—	✓ apache-2.0	2.5 M	—
18	wav2vec2-large-xlsr-53-arabic jonatasgrosman · ASR	—	—	✓ apache-2.0	2.4 M	—
19	Qwen3-ASR-1.7B Qwen · ASR	2.4 B	—	✓ apache-2.0	2.3 M	from 6.0 GB
20	romanian-wav2vec2 gigant · ASR	320 M	—	✓ apache-2.0	1.9 M	from 1.9 GB
21	wav2vec2-large-voxrex-swedish KBLab · ASR	320 M	—	✓ cc0-1.0	1.9 M	from 1.9 GB
22	Voxtral-Mini-4B-Realtime-2602 mistralai · ASR	4.4 B	—	✓ apache-2.0	1.9 M	from 20.7 GB
23	wav2vec2-large-xlsr-53-telugu anuragshas · ASR	—	—	✓ apache-2.0	1.9 M	—
24	nemotron-3.5-asr-streaming-0.6b-gguf handy-computer · ASR	—	—	other	1.8 M	from 1.0 GB
25	parakeet-tdt-0.6b-v3 mlx-community · ASR	630 M	—	✓ cc-by-4.0	1.8 M	from 3.4 GB
26	filipino-wav2vec2-l-xls-r-300m-official Khalsuu · ASR	300 M	—	✓ apache-2.0	1.8 M	from 1.2 GB
27	wav2vec2-large-xlsr-53-persian jonatasgrosman · ASR	—	—	✓ apache-2.0	1.8 M	—
28	wav2vec2-large-xls-r-300m-Urdu kingabzpro · ASR	320 M	—	✓ apache-2.0	1.7 M	from 1.9 GB
29	faster-whisper-base Systran · ASR	—	—	✓ mit	1.7 M	—
30	whisper-tiny openai · ASR	40 M	—	✓ apache-2.0	1.7 M	from 0.7 GB
31	whisper-base openai · ASR	70 M	—	✓ apache-2.0	1.6 M	from 0.8 GB
32	parakeet-unified-en-0.6b-gguf handy-computer · ASR	—	—	✓ cc-by-4.0	1.6 M	from 1.0 GB
33	wav2vec2-large-xlsr-53-th airesearch · ASR	—	—	cc-by-sa-4.0	1.5 M	—
34	wav2vec2-base-960h facebook · ASR	90 M	—	✓ apache-2.0	1.5 M	from 0.9 GB
35	vakyansh-wav2vec2-tamil-tam-250 Harveenchadha · ASR	—	—	✓ mit	1.4 M	—
36	wav2vec2-large-xlsr-53-chinese-zh-cn jonatasgrosman · ASR	—	—	✓ apache-2.0	1.4 M	—
37	wav2vec2-xls-r-300m-mixed mesolitica · ASR	300 M	—	unknown	1.4 M	from 1.2 GB
38	voice-activity-detection pyannote · ASR · gated	—	—	✓ mit	1.4 M	—
39	Wav2Vec2-large-xlsr-hindi theainerd · ASR	320 M	—	unknown	1.4 M	from 1.9 GB
40	wav2vec2-base-vi-vlsp2020 nguyenvulebinh · ASR	—	—	✗ cc-by-nc-4.0	1.3 M	—
41	wav2vec2-large-xlsr-53-finnish jonatasgrosman · ASR	—	—	✓ apache-2.0	1.3 M	—
42	wav2vec2-xls-r-300m-cs-250 comodoro · ASR	320 M	—	✓ apache-2.0	1.3 M	from 1.9 GB
43	wav2vec2-xls-r-300m-hebrew imvladikon · ASR	320 M	—	unknown	1.3 M	from 1.9 GB
44	nb-wav2vec2-1b-nynorsk NbAiLab · ASR	960 M	—	✓ apache-2.0	1.2 M	from 4.9 GB
45	whisper-tiny Xenova · ASR	40 M	—	✓ apache-2.0	1.2 M	from 0.6 GB
46	wav2vec2-xls-r-300m-bengali arijitx · ASR	300 M	—	✓ apache-2.0	1.1 M	from 1.2 GB
47	wav2vec2-xls-r-parlaspeech-hr classla · ASR	320 M	—	unknown	1.1 M	from 1.9 GB
48	parakeet-tdt-0.6b-v2 mlx-community · ASR	620 M	—	✓ cc-by-4.0	1.1 M	from 3.3 GB
49	nb-wav2vec2-1b-bokmaal-v2 NbAiLab · ASR	960 M	—	✓ apache-2.0	1.0 M	from 4.9 GB
50	w2v-xls-r-uk Yehor · ASR	320 M	—	✓ apache-2.0	1.0 M	from 1.9 GB

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