Harveenchadha / automatic-speech-recognition updated 4 years ago

vakyansh-wav2vec2-tamil-tam-250

Fine-tuned on Multilingual Pretrained Model CLSRIL-23. The original fairseq checkpoint is present here. When using this model, make sure that your speech input is sampled at 16kHz.

Params
Context
Downloads 30d
1.4 M
Likes
4
Commercial use: allowed mit Not gated 1 languages View on Hugging Face ↗

Download history

daily snapshots · 55 days
▲ 605 K in the last 30 days (73.8%)
1.7 M621 K
Jul 28Aug 15Sep 2Sep 20

Specifications

Architecture
Wav2Vec2ForCTC
Vocabulary
53
Layers / heads
12 / 12
Licence
mit
First seen on the Hub
2022-03-02
Training datasets
undisclosed
Common Voice ta (reported)
53.64
Added to our catalog
2026-07-28
Compare with any automatic-speech-recognition model