mpoyraz / automatic-speech-recognition updated 4 years ago

wav2vec2-xls-r-300m-cv7-turkish

This ASR model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on Turkish language.

Params
300 M
Context
Downloads 30d
558 K
Likes
16
Commercial use: allowed cc-by-4.0 Not gated 1 languages View on Hugging Face ↗

Download history

daily snapshots · 55 days
▲ 49 K in the last 30 days (9.7%)
576 K409 K
Jul 28Aug 15Sep 2Sep 20

Specifications

Architecture
Wav2Vec2ForCTC
Parameters
300 M
Vocabulary
38
Layers / heads
24 / 16
Licence
cc-by-4.0
First seen on the Hub
2022-03-02
Training datasets
mozilla-foundation/common_voice_7_0
Common Voice 7 (reported)
2.26
Robust Speech Event - Dev Data (reported)
10.69
Robust Speech Event - Test Data (reported)
32.09
Added to our catalog
2026-07-28
Compare with any automatic-speech-recognition model