softcatala / automatic-speech-recognition Open weights updated 4 years ago

wav2vec2-large-xlsr-catala

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Catalan language using the Common Voice and ParlamentParla datasets.

Params
—
Context
—
Downloads 30d
737 K
Likes
4
Commercial use: allowed apache-2.0 Not gated 1 languages View on Hugging Face ↗

Download history

daily snapshots · 106 days
▲ 273 K in the last 30 days (58.7%)
929 K320 K
Jul 28Sep 1Oct 6Nov 10

Specifications

Architecture
Wav2Vec2ForCTC
Vocabulary
42
Layers / heads
24 / 16
Licence
apache-2.0
First seen on the Hub
2022-03-02
Training datasets
common_voice, parlament_parla
Test WER (reported)
6.92
Google Crowsourced Corpus WER (reported)
12.99
Audiobook “La llegenda de Sant Jordi” WER (reported)
13.23
Added to our catalog
2026-07-28
Compare with any automatic-speech-recognition model