comodoro / automatic-speech-recognition updated 4 years ago

wav2vec2-xls-r-300m-sk-cv8

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the commonvoice 8.0 dataset. It achieves the following results on the evaluation set:

Params
300 M
Context
Downloads 30d
505 K
Likes
0
Commercial use: allowed apache-2.0 Not gated 1 languages View on Hugging Face ↗

Download history

daily snapshots · 49 days
▲ 122 K in the last 30 days (31.8%)
585 K378 K
Aug 3Aug 19Sep 4Sep 20

Specifications

Architecture
Wav2Vec2ForCTC
Parameters
300 M
Vocabulary
49
Layers / heads
24 / 16
Licence
apache-2.0
First seen on the Hub
2022-03-02
Training datasets
common_voice
Common Voice 8 (reported)
13.3
Robust Speech Event - Dev Data (reported)
81.7
Robust Speech Event - Test Data (reported)
80.26
Added to our catalog
2026-08-03
Compare with any automatic-speech-recognition model