jonatasgrosman / automatic-speech-recognition updated 3 years ago

wav2vec2-large-xlsr-53-portuguese

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Portuguese using the train and validation splits of Common Voice 6.1. When using this model, make sure that your speech input is sampled at 16kHz.

Params
Context
Downloads 30d
6.0 M
Likes
58
Commercial use: allowed apache-2.0 Not gated 1 languages View on Hugging Face ↗

Download history

daily snapshots · 55 days
▲ 1.0 M in the last 30 days (20.7%)
6.0 M3.9 M
Jul 28Aug 15Sep 2Sep 20

Specifications

Architecture
Wav2Vec2ForCTC
Vocabulary
46
Layers / heads
24 / 16
Licence
apache-2.0
First seen on the Hub
2022-03-02
Training datasets
common_voice, mozilla-foundation/common_voice_6_0
Common Voice pt (reported)
3.21
Robust Speech Event - Dev Data (reported)
16.88
Added to our catalog
2026-07-28
Compare with any automatic-speech-recognition model