Modelpublic

KSE-RESEARCH-Group/wav2vec2-uk-dido-yvanchyk

sourceHugging Faceapache-2.0updated 8mo agoView on Hugging Face

0likes27downloads

Model Card

wav2vec2-uk-dido-yvanchyk - Ukrainian ASR

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the Dido Yvanchyk Audio Dataset v2.

Model Description

The model was fine-tuned for 50 epochs to improve ASR quality for Ukrainian conversational speech and local dialects.

Usage

python

from transformers import pipeline

pipe = pipeline("automatic-speech-recognition", model="KSE-RESEARCH-Group/wav2vec2-uk-dido-yvanchyk")
print(pipe("sample.wav")["text"])