W

Wav2vec2 Xlsr Georgian

Developed by sammy786
This model is an automatic speech recognition model fine-tuned on Georgian language datasets based on facebook/wav2vec2-xls-r-1b
Downloads 19
Release Time : 3/2/2022

Model Overview

Georgian automatic speech recognition model based on the wav2vec2-xls-r-1b architecture, fine-tuned on the Common Voice 8 dataset

Model Features

High-performance speech recognition
Achieves a 23.9% word error rate (WER) on the Common Voice 8 Georgian test set
Large-scale pre-training
Fine-tuned based on the 1-billion-parameter wav2vec2-xls-r-1b model
Multi-scenario adaptation
Evaluated on dialogue and robust speech event datasets

Model Capabilities

Georgian speech-to-text
Automatic speech recognition
Conversational speech processing

Use Cases

Speech transcription
Georgian speech transcription
Convert Georgian speech into text
23.9% WER on the Common Voice test set
Dialogue systems
Georgian dialogue processing
Process Georgian conversational speech
74.41% WER on the robust speech event test set
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase