1,423 models · 1,213 open weights · 210 API-only · refreshed nightly

Automatic speech recognition models

Every model in the catalog — open weights you can self-host and API-only models — with licence or API price, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.

#ModelParamsContextCommercial use30dMin VRAM
01 whisperkit-coreml argmaxinc · ASR Open weights — — ✓ mit 51.6 M —
02 wav2vec2-large-xlsr-53-japanese jonatasgrosman · ASR Open weights — — ✓ apache-2.0 16.2 M —
03 speaker-diarization-3.1 pyannote · ASR · gated Open weights — — ✓ mit 6.7 M —
04 faster-whisper-small Systran · ASR Open weights — — ✓ mit 5.7 M —
05 whisper-large-v3-turbo openai · ASR Open weights 810 M — ✓ mit 5.2 M from 2.4 GB
06 speaker-diarization-community-1 pyannote · ASR · gated Open weights — — ✓ cc-by-4.0 5.1 M —
07 whisper-base openai · ASR Open weights 70 M — ✓ apache-2.0 4.6 M from 0.8 GB
08 whisper-small openai · ASR Open weights 240 M — ✓ apache-2.0 4.4 M from 1.6 GB
09 wav2vec2-large-xlsr-53-russian jonatasgrosman · ASR Open weights — — ✓ apache-2.0 3.8 M —
10 wav2vec2-large-xlsr-53-portuguese jonatasgrosman · ASR Open weights — — ✓ apache-2.0 3.6 M —
11 whisper-large-v3 openai · ASR Open weights 1.5 B — ✓ apache-2.0 3.5 M from 10.9 GB
12 parakeet-tdt-0.6b-v3 mlx-community · ASR Open weights 630 M — ✓ cc-by-4.0 2.7 M from 3.4 GB
13 wav2vec2-large-xlsr-53-polish jonatasgrosman · ASR Open weights — — ✓ apache-2.0 2.5 M —
14 mms-300m-1130-forced-aligner MahmoudAshraf · ASR Open weights 320 M — ✗ cc-by-nc-4.0 2.4 M from 1.9 GB
15 faster-whisper-tiny Systran · ASR Open weights — — ✓ mit 2.4 M —
16 parakeet-unified-en-0.6b-gguf handy-computer · ASR Open weights 600 M — other 2.4 M from 1.1 GB
17 wav2vec2-large-xlsr-53-dutch jonatasgrosman · ASR Open weights — — ✓ apache-2.0 2.3 M —
18 wav2vec2-large-xlsr-53-arabic jonatasgrosman · ASR Open weights — — ✓ apache-2.0 2.2 M —
19 faster-whisper-base Systran · ASR Open weights — — ✓ mit 2.2 M —
20 wav2vec2-large-xlsr-53-greek jonatasgrosman · ASR Open weights — — ✓ apache-2.0 2.0 M —
21 nemotron-3.5-asr-streaming-0.6b-gguf handy-computer · ASR Open weights 600 M — other 2.0 M from 1.1 GB
22 faster-whisper-medium Systran · ASR Open weights — — ✓ mit 2.0 M —
23 wav2vec2-large-xlsr-53-chinese-zh-cn jonatasgrosman · ASR Open weights — — ✓ apache-2.0 1.9 M —
24 wav2vec2-base-960h facebook · ASR Open weights 90 M — ✓ apache-2.0 1.8 M from 0.9 GB
25 wav2vec2-indonesian-javanese-sundanese indonesian-nlp · ASR Open weights — — ✓ apache-2.0 1.7 M —
26 Qwen3-ASR-1.7B Qwen · ASR Open weights 2.4 B — ✓ apache-2.0 1.7 M from 6.0 GB
27 wav2vec2-large-xlsr-53-hungarian jonatasgrosman · ASR Open weights — — ✓ apache-2.0 1.7 M —
28 faster-whisper-large-v3 Systran · ASR Open weights — — ✓ mit 1.6 M —
29 Voxtral-Mini-4B-Realtime-2602 mistralai · ASR Open weights 4.4 B — ✓ apache-2.0 1.5 M from 20.7 GB
30 faster-whisper-small.en Systran · ASR Open weights — — ✓ mit 1.4 M —
31 wav2vec2-xls-r-300m-cs-250 comodoro · ASR Open weights 320 M — ✓ apache-2.0 1.4 M from 1.9 GB
32 wav2vec2-large-xlsr-53-th airesearch · ASR Open weights — — cc-by-sa-4.0 1.3 M —
33 wav2vec2-large-voxrex-swedish KBLab · ASR Open weights 320 M — ✓ cc0-1.0 1.3 M from 1.9 GB
34 Qwen3-ASR-1.7B-gguf handy-computer · ASR Open weights 1.7 B — ✓ apache-2.0 1.2 M from 2.2 GB
35 cohere-transcribe-03-2026-gguf handy-computer · ASR Open weights 2.1 B — ✓ apache-2.0 1.2 M from 2.5 GB
36 faster-whisper-base.en Systran · ASR Open weights — — ✓ mit 1.2 M —
37 wav2vec2-large-xlsr-53-finnish jonatasgrosman · ASR Open weights — — ✓ apache-2.0 1.2 M —
38 romanian-wav2vec2 gigant · ASR Open weights 320 M — ✓ apache-2.0 1.2 M from 1.9 GB
39 parakeet-tdt-0.6b-v3-gguf handy-computer · ASR Open weights 600 M — ✓ cc-by-4.0 1.1 M from 1.1 GB
40 wav2vec2-large-xlsr-korean kresnik · ASR Open weights 320 M — ✓ apache-2.0 1.1 M from 1.9 GB
41 wav2vec2-base-vi-vlsp2020 nguyenvulebinh · ASR Open weights — — ✗ cc-by-nc-4.0 1.1 M —
42 wav2vec2-xls-r-300m-mixed mesolitica · ASR Open weights 300 M — unknown 1.1 M from 1.2 GB
43 filipino-wav2vec2-l-xls-r-300m-official Khalsuu · ASR Open weights 300 M — ✓ apache-2.0 1.1 M from 1.2 GB
44 wav2vec2-large-xls-r-300m-Urdu kingabzpro · ASR Open weights 320 M — ✓ apache-2.0 1.1 M from 1.9 GB
45 wav2vec2-xls-r-parlaspeech-hr classla · ASR Open weights 320 M — unknown 1.0 M from 1.9 GB
46 wav2vec2-large-xlsr-53-telugu anuragshas · ASR Open weights — — ✓ apache-2.0 1.0 M —
47 wav2vec2-xls-r-300m-hebrew imvladikon · ASR Open weights 320 M — unknown 1.0 M from 1.9 GB
48 parakeet-ultra-gguf handy-computer · ASR Open weights — — ✓ cc-by-4.0 1,000 K from 1.0 GB
49 wav2vec2-xls-r-300m-cv7-turkish mpoyraz · ASR Open weights 300 M — ✓ cc-by-4.0 991 K from 1.2 GB
50 nb-wav2vec2-1b-bokmaal-v2 NbAiLab · ASR Open weights 960 M — ✓ apache-2.0 947 K from 4.9 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.