AIbase
EN
Home
W2v Xls R Uk
W

W2v Xls R Uk

Developed by Yehor
Ukrainian automatic speech recognition model based on facebook/wav2vec2-xls-r-300m, trained on the Common Voice 10.0 dataset
Speech Recognition
Transformers
 OtherOpen Source License:Apache-2.0#Ukrainian speech recognition#Low word error rate#Efficient inference
Downloads 231.46k
Release Time : 6/8/2022

Model Overview

This is an Ukrainian automatic speech recognition (ASR) model capable of converting Ukrainian speech into text. Based on Facebook's wav2vec2-xls-r-300m architecture, fine-tuned on the Mozilla Common Voice 10.0 Ukrainian dataset.

Model Features

High accuracy
Achieves a word error rate (WER) of 20.24% and a character error rate (CER) of 3.64% on Ukrainian test sets
Based on a powerful foundation model
Uses Facebook's wav2vec2-xls-r-300m as the base model, featuring robust speech feature extraction capabilities
Community support
Supported by an active Ukrainian speech technology community, including Discord and Telegram discussion groups

Model Capabilities

Ukrainian speech recognition
Speech-to-text conversion

Use Cases

Speech transcription
Ukrainian speech transcription
Converts Ukrainian speech content into text
79.76% accuracy (word-level)
Voice assistants
Ukrainian voice command recognition
Used to build Ukrainian voice assistants or command control systems
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
EnglishįŽ€äŊ“中文įšéĢ”中文ãĢãģんご
Š 2025AIbase