mesolitica / automatic-speech-recognition updated 4 years ago

wav2vec2-xls-r-300m-mixed

Finetuned https://huggingface.co/facebook/wav2vec2-xls-r-300m on https://github.com/huseinzol05/malaya-speech/tree/master/data/mixed-stt

Params
300 M
Context
Downloads 30d
1.4 M
Likes
5
Licence: unknown Not gated View on Hugging Face ↗

Download history

daily snapshots · 55 days
▲ 615 K in the last 30 days (78.8%)
1.6 M561 K
Jul 28Aug 15Sep 2Sep 20

Specifications

Architecture
Wav2Vec2ForCTC
Parameters
300 M
Vocabulary
40
Layers / heads
24 / 16
First seen on the Hub
2022-06-01
Training datasets
undisclosed
Added to our catalog
2026-07-28
Compare with any automatic-speech-recognition model