W

Wav2vec2 Large Xlsr 53 Lithuanian

Developed by DeividasM
A Lithuanian speech recognition model fine-tuned from Facebook's XLSR-53 large model, trained on the Common Voice dataset with a test WER of 56.55%.
Downloads 4,105
Release Time : 3/2/2022

Model Overview

This model is an automatic speech recognition (ASR) system optimized for Lithuanian, suitable for converting Lithuanian audio into text.

Model Features

XLSR Fine-tuning
Fine-tuned from Facebook's XLSR-53 large model to adapt to Lithuanian language characteristics
16kHz Sampling Rate Support
Specifically optimized for processing speech input at 16kHz sampling rate
No Language Model Required
Can be used directly without additional language model support

Model Capabilities

Lithuanian speech recognition
Audio-to-text conversion
Automatic speech transcription

Use Cases

Speech Transcription
Speech-to-Text Service
Automatically convert Lithuanian speech content into text
Test WER 56.55%
Voice Assistant
Support for Lithuanian voice interaction systems
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase