Open-source model wav2vec2-xls-r-300m-W2V2-XLSR-300M-YAKUT-SMALL - Accurately achieve Yakut speech recognition

Wav2vec2 Xls R 300m W2V2 XLSR 300M YAKUT SMALL

Developed by emre

This is a speech recognition model fine-tuned on the Yakut (Sakha) language dataset based on the facebook/wav2vec2-xls-r-300m model

Downloads 90

Release Time : 3/2/2022

Model Overview

This model is an automatic speech recognition (ASR) model optimized for the Yakut (Sakha) language, fine-tuned on the Common Voice dataset

Yakut language optimization

Specially fine-tuned for the Yakut (Sakha) language, improving recognition accuracy for this language

Based on XLS-R architecture

Uses Facebook's wav2vec2-xls-r-300m as the base model, with powerful speech feature extraction capabilities

Trained on Common Voice dataset

Trained on the Yakut language dataset from Common Voice, ensuring data diversity

Speech recognition

Yakut speech-to-text

Speech transcription

Yakut speech transcription

Convert Yakut speech content into text

WER of 79.0 on the test set

Voice assistants

Yakut voice command recognition

Used for voice assistant systems supporting the Yakut language

Training Loss	Epoch	Step	Validation Loss	Wer
4.6926	19.05	400	2.7538	1.0
0.7031	38.1	800	0.9068	0.7900

Property	Details
Model Type	wav2vec2-xls-r-300m-W2V2-XLSR-300M-YAKUT-SMALL
Training Data	common_voice

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base