AIbase
EN
Home
Wav2vec2 Common Voice Lithuanian
W

Wav2vec2 Common Voice Lithuanian

Developed by birgermoell
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the COMMON_VOICE - LT dataset for Lithuanian speech recognition.
Speech Recognition
Transformers
 OtherOpen Source License:Apache-2.0#Lithuanian speech recognition#Multilingual support#High-precision WER
Downloads 17
Release Time : 4/20/2022

Model Overview

This is an automatic speech recognition (ASR) model optimized for Lithuanian, based on the wav2vec2 architecture and fine-tuned on the Common Voice Lithuanian dataset.

Model Features

Lithuanian optimization
Specially fine-tuned for Lithuanian to improve recognition accuracy for this language.
Based on wav2vec2 architecture
Uses facebook's wav2vec2-large-xlsr-53 as the base model, featuring powerful speech feature extraction capabilities.
Trained on Common Voice dataset
Fine-tuned using the Common Voice Lithuanian dataset to ensure data quality and diversity.

Model Capabilities

Lithuanian speech recognition
Speech-to-text

Use Cases

Speech transcription
Lithuanian speech transcription
Convert Lithuanian speech content into text
Achieved a Word Error Rate (WER) of 0.6546 on the evaluation set.
Voice assistants
Lithuanian voice command recognition
Used for Lithuanian voice assistants or smart home device voice command recognition
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