Model · Hugging Face

facebook/wav2vec2-base-960h

Name: wav2vec2-base-960h
Author: facebook

Author / organization	facebook
License (as declared)	apache-2.0
Downloads	1.8M (as reported by Hugging Face)
Likes	410
Task	automatic-speech-recognition
Library	transformers
Created	2 March 2022
Last updated at source	—

transformerspytorchtfsafetensorswav2vec2automatic-speech-recognitionaudiohf-asr-leaderboardenmodel-indexeval-resultsendpoints_compatible

Embed this entry

<iframe src="https://silytics.si/embed/item/175c0a18-d166-4892-b1f8-879aeeb60417" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Reported results

Dataset	Metric	Value
LibriSpeech (clean) · test	Test WER	3.4
LibriSpeech (other) · test	Test WER	8.6

Reported by the model's authors in the model card. Not independently verified, and setups differ between authors, so scores from different models are not always comparable. Each value links to its source.

More from facebook

Silytics shows public metadata from Hugging Face and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.