wav2vec2-base-960h
facebook/wav2vec2-base-960h
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 1.6M
- Total downloadsCumulative all-time download counter reported by the source platform.
- 118.4M
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +367.6K(increase)
- 0.3%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 406
- +1 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #25 among tracked Speech Recognition models.
- #252
- 25(up 25 places)this week
- Parameters
- 94.4M
- Last source update
- Nov 14, 2022
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 81.9
- wav2vec2-base-960h gained 367.6K downloads during the last seven tracked days.
- It moved from #27 to #25 among tracked Speech Recognition models this week.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
wav2vec2-base-960h is a speech recognition model published by facebook. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Sep 30, 2026.
- Published
- Mar 2, 2022
- Last updated
- Nov 14, 2022
- Library
- transformers
- License
- apache-2.0
- Task
- Speech Recognition
- Parameters
- 94,395,552
- Spaces
- —
- Derivative models
- 4
- Velocity 7D/day
- 52.5K
transformerspytorchtfsafetensorswav2vec2automatic-speech-recognitionaudiohf-asr-leaderboardendataset:librispeech_asrarxiv:2006.11477license:apache-2.0
Publisher
facebookView publisher statistics →Model family
Based on base-model relationships reported by the source's metadata.
Derivative models
Similar models
| Model | DL 30D |
|---|---|
| wav2vec2-french-phonemizer-v2Cnam-LMSSC | 9,765 |
| wav2vec2-base-760-turkishceyda | 714 |
| wav2vec2-italian-phonemizerCnam-LMSSC | 435 |
| wav2vec2-quran-phoneticsTBOGamer22 | 8,862 |
| wav2vec2-spanish-phonemizerCnam-LMSSC | 784 |
| wav2vec2-ljspeech-gruutbookbot | 6,166 |