whatmodel.sh / stt / wav2vec 2.0 Large Robust (LibriSpeech 960h ft)

wav2vec 2.0 Large Robust (LibriSpeech 960h ft)

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

wav2vec 2.0 Large Robust (LibriSpeech 960h ft) is an open-weights speech-to-text model from Meta, released April 2021. Its published size is 0.32B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact checkpoint facebook/wav2vec2-large-robust-ft-libri-960h (CTC fine-tuned on LibriSpeech 960h). Params: HF safetensors total; released: arXiv 2104.01027v1 month.

14.9±4.6#153 of 162 speech-to-text modelsfrom 4 benchmark results across 3 sources

Score within the Open ASR English short-form WER (March 2026) comparison set only.

$ how it compares

The speech-to-text models ranked either side of wav2vec 2.0 Large Robust (LibriSpeech 960h ft), out of 176 with a score, then more from Meta.

#modelscorewhereRAMreleased
165HuBERT X-Large (LibriSpeech 960h ft) Meta16±4local~5.1GB2021-06
166HuBERT Large (LibriSpeech 960h ft) Meta15±4local~2GB2021-06
167wav2vec 2.0 Large Robust (LibriSpeech 960h ft) Meta15±5local~2GB2021-04
168Whisper tiny OpenAI14±3local~0.6GB2022-09
169wav2vec 2.0 Conformer Rel-Pos Large 960h Meta14±4local~3.5GB2022-04
more from Meta
1Muse Voice Transcribe 1.0 Meta71±3api $0.0030/audio min2026-09
58Omnilingual ASR LLM 7B Meta58±2local~19GB2025-11
59Omnilingual ASR LLM 7B v2 Meta58±3local~19GB2025-12

see all speech-to-text models · find the ones that fit your machine

$ what it's good at

other tests4 not in a task · 92% of its score
testresultvs the others in its rundifficultycountswhy
Open ASR English short-form WER (March 2026)22.9% ✎▁▁▁▃··▁▁▂██▆ beats 7/86avg 8.2%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 74%blunt
Speech Accessibility Project dysarthric speech · zero-shot WER (rated subset, N=11,218)32.6% ✎▂·▃··▂····▆█ beats 1/9avg 18%▇▇▇ 8.5%blunt
TED-LIUM test WER (short-form)15.2% ✎▂····▂▂▃█▃▃▂ beats 3/13avg 9.2%▇▇ 5.4%blunt
LibriSpeech test-clean WER2.6% ✎▂··▂·▃▂█▂▃▃▃ beats 12/16avg 1.7%▇▇ 4.2%blunt · noisy

$ where to run it

Other ways to run it

  1. Run it as published · needs ~2.04 GB · from huggingface.co/facebook
    uv run --with transformers --with torch python -c "from transformers import pipeline; print(pipeline('automatic-speech-recognition', model='facebook/wav2vec2-large-robust-ft-libri-960h', chunk_length_s=30)('audio.wav')['text'])"

Weights and documentation: huggingface.co/facebook ↗

$ how the score was worked out · Open ASR Leaderboard 74%, Speech Robust Bench (arXiv:24… 10%, Dysarthric ASR with clinical… 8%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Open ASR Leaderboard1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 74%Apache-2.0
Speech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR models2▇▇▇ 10%CC BY 4.0
Dysarthric ASR with clinical context on the Speech Accessibility Project (arXiv:2605.02782v2)1▇▇▇ 8%CC BY 4.0
prior · pull toward the middle▇▇ 8%
weighted average= 14.9

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json