Yehor
/

flashlight-uk

Automatic Speech Recognition

Eval Results (legacy)

Model card Files Files and versions

Yehor commited on Feb 20, 2025

Commit

c807be4

·

verified ·

1 Parent(s): c85a00a

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -43,7 +43,7 @@ See other Ukrainian models: https://github.com/egorsmkv/speech-recognition-uk
 This repository contains the acoustic model for Ukrainian trained on Flashlight framework: https://github.com/flashlight/flashlight/tree/main/flashlight/app/asr
-- Architecture: Conformer (30m params)
 - Data in train: Common Voice 10 & Voice of America
 - Trained epochs: 410
 - Train time: around a week (RTX A4000)

 This repository contains the acoustic model for Ukrainian trained on Flashlight framework: https://github.com/flashlight/flashlight/tree/main/flashlight/app/asr
+- Architecture: Conformer (300m params)
 - Data in train: Common Voice 10 & Voice of America
 - Trained epochs: 410
 - Train time: around a week (RTX A4000)