W

Wav2vec2 Large Xls R 300m Sakha

Developed by infinitejoy
Automatic speech recognition model fine-tuned on Yakut (SAH) dataset based on facebook/wav2vec2-xls-r-300m
Downloads 18
Release Time : 3/2/2022

Model Overview

This is an automatic speech recognition (ASR) model specifically optimized for the Yakut language, based on the XLS-R-300M architecture and fine-tuned on the Yakut dataset from Common Voice 7.

Model Features

Yakut language optimization
Specially fine-tuned for Yakut language, outperforming general speech models on this language
Based on XLS-R architecture
Utilizes the powerful XLS-R-300M architecture with excellent speech feature extraction capabilities
Medium scale
300M parameter size, balancing performance and resource consumption

Model Capabilities

Yakut speech recognition
Speech-to-text
Robust speech processing

Use Cases

Speech transcription
Yakut speech transcription
Convert Yakut speech content into text
CER:10.271%, WER:44.196%
Voice assistant
Yakut voice interaction
Provide voice interaction capability for Yakut-speaking users
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase