wav2vec2-large-xlsr-53-polish

jonatasgrosman/wav2vec2-large-xlsr-53-polish

Speech RecognitiontransformersLicense: apache-2.0
Tracked by OpenModelStats since September 25, 2026View on Hugging Face ↗
Downloads 30D
2.2M
Total downloads
39.7M
Gained 7D
+855.4K(increase)
2.3%(up) vs baseline
Gained 30D
—
Likes
14
+2 in 7D
Rank · tracked models
#188
50(down 50 places)this week
Parameters
—
Last source update
Dec 14, 2022
Momentum
90.4
  • wav2vec2-large-xlsr-53-polish gained 855.4K downloads during the last seven tracked days.
  • It moved from #11 to #13 among tracked Speech Recognition models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

wav2vec2-large-xlsr-53-polish is a speech recognition model published by jonatasgrosman. OpenModelStats has tracked the model since Sep 25, 2026, most recently observing it Oct 2, 2026.

Published
Mar 2, 2022
Last updated
Dec 14, 2022
Library
transformers
License
apache-2.0
Task
Speech Recognition
Parameters
—
Spaces
—
Derivative models
—
Velocity 7D/day
122.2K
transformerspytorchjaxwav2vec2automatic-speech-recognitionaudiohf-asr-leaderboardmozilla-foundation/common_voice_6_0plrobust-speech-eventspeechxlsr-fine-tuning-week

Similar models

Models similar to wav2vec2-large-xlsr-53-polish
ModelDL 30D
wav2vec2-large-xlsr-53-japanesejonatasgrosman16.4M
whisperkit-coremlargmaxinc10.8M
speaker-diarization-3.1pyannote7.2M
whisper-large-v3-turboopenai6.4M
wav2vec2-large-xlsr-53-portuguesejonatasgrosman5.6M
speaker-diarization-community-1pyannote5.5M