W

Wav2vec2 Large Xlsr 53 Lithuanian

Developed by dundar
A Lithuanian speech recognition model fine-tuned on the Common Voice dataset based on facebook/wav2vec2-large-xlsr-53
Downloads 25
Release Time : 3/2/2022

Model Overview

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

Model Features

High-accuracy Lithuanian recognition
Achieves a word error rate (WER) of 35.87% on the Common Voice Lithuanian test set
Based on XLSR pre-trained model
Fine-tuned from facebook/wav2vec2-large-xlsr-53 model, utilizing cross-lingual speech representation learning
No language model required
Can be used directly without additional language model support

Model Capabilities

Lithuanian speech recognition
16kHz audio processing

Use Cases

Speech-to-text
Lithuanian speech transcription
Convert Lithuanian speech to text
Word error rate 35.87%
Voice assistants
Lithuanian voice command recognition
For Lithuanian voice assistants or voice control applications
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase