W

Wav2vec2 Large Xlsr 53 Estonian

Developed by anton-l
Estonian speech recognition model fine-tuned from Facebook's XLSR-53 large model, achieving 30.74% word error rate on Common Voice dataset
Downloads 3,259
Release Time : 3/2/2022

Model Overview

This is an automatic speech recognition (ASR) model specifically optimized for Estonian, fine-tuned based on Wav2Vec2-Large-XLSR-53 architecture, suitable for 16kHz sampled audio input.

Model Features

High Accuracy Estonian Recognition
Speech recognition model specifically optimized for Estonian, achieving 30.74% word error rate on Common Voice test set
Based on XLSR Large Model
Fine-tuned from Facebook's powerful multilingual pre-trained model Wav2Vec2-Large-XLSR-53
No Language Model Required
Can be used directly without additional language model support

Model Capabilities

Estonian speech recognition
16kHz audio processing
End-to-end speech-to-text

Use Cases

Speech Transcription
Estonian Speech to Text
Convert Estonian speech content into text
30.74% word error rate
Voice Assistants
Estonian Voice Command Recognition
For supporting Estonian-language voice assistants and smart devices
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase