whatmodel.sh / stt / HuBERT Large (LibriSpeech 960h ft)
HuBERT Large (LibriSpeech 960h ft)
↗ share
+ contribute
HuBERT Large (LibriSpeech 960h ft) is an open-weights speech-to-text model from Meta, released June 2021. Its published size is 0.32B parameters. Licence: apache-2.0.
Catalogue identity notes
Exact checkpoint facebook/hubert-large-ls960-ft (CTC fine-tuned on LibriSpeech 960h). Params: fp32 pytorch_model.bin 1,262,057,559 bytes / 4; released: arXiv 2106.07447v1 month.
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 HuBERT Large (LibriSpeech 960h ft), out of 176 with a score, then more from Meta.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 164 | wav2vec 2.0 Large 960h LV-60 self-training | 16±3 | local | ||
| 165 | HuBERT X-Large (LibriSpeech 960h ft) | 16±4 | local | ||
| 166 | HuBERT Large (LibriSpeech 960h ft) | 15±4 | local | ||
| 167 | wav2vec 2.0 Large Robust (LibriSpeech 960h ft) | 15±5 | local | ||
| 168 |  Whisper tiny | 14±3 | local | ||
| more from Meta | |||||
| 1 | Muse Voice Transcribe 1.0 | 71±3 | api $0.0030/audio min | ||
| 58 | Omnilingual ASR LLM 7B | 58±2 | local | ||
| 59 | Omnilingual ASR LLM 7B v2 | 58±3 | local | ||
see all speech-to-text models · find the ones that fit your machine
$ what it's good at
other tests3 not in a task · 93% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Open ASR English short-form WER (March 2026) | 22.7% ✎ | ▁▁▁▃··▁▁▂██▆ beats 8/86 | 64% |
| LibriSpeech test-clean WER +1 | 2.1% ✎ | ▂··▂·▃▂█▂▃▃▃ beats 14/16 | 24% |
| TED-LIUM test WER (short-form) | 14.7% ✎ | ▂····▂▂▂█▃▃▂ beats 5/13 | 4.7% |
$ where to run it
Other ways to run it
- 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/hubert-large-ls960-ft', chunk_length_s=30)('audio.wav')['text'])"
Weights and documentation: huggingface.co/facebook ↗
$ how the score was worked out · Open ASR Leaderboard 64%, Meta (facebook org) Hugging F… 20%, Speech Robust Bench (arXiv:24… 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
| source | results | share of the score |
|---|---|---|
 Open ASR Leaderboard | 1 | 64% |
| Meta (facebook org) Hugging Face ASR model cards: published LibriSpeech WER for its own checkpoints · lab-reported | 1 | 20% |
 Speech Robust Bench (arXiv:2403.07937v3) · clean-speech WER of 25+ open ASR models | 2 | 8% |
| prior · pull toward the middle | 7% | |
| weighted average | = 15.3 |
$ improve this page
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