W

Wav2vec2 Xls R 300m Sk Cv8

Developed by comodoro
Speech recognition model fine-tuned on the Common Voice 8.0 Slovak dataset based on facebook/wav2vec2-xls-r-300m
Downloads 64.15k
Release Time : 3/2/2022

Model Overview

This is an automatic speech recognition (ASR) model for Slovak language, based on Wav2Vec2 XLSR architecture and fine-tuned on Common Voice 8.0 dataset.

Model Features

High-performance speech recognition
Achieves 49.6% WER and 13.3% CER on Common Voice 8.0 test set
No language model required
Can be used directly without additional language model support
Multi-dataset adaptation
Evaluation results available on both Common Voice and Robust Speech Event datasets

Model Capabilities

Slovak speech recognition
Automatic speech-to-text
Audio content understanding

Use Cases

Speech transcription
Voice memo to text
Automatically convert Slovak voice memos into editable text
Approximately 50.4% accuracy (1-WER)
Voice interaction systems
Slovak voice assistant
Provide voice interaction interface for Slovak users
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase