W

Wav2vec2 Large Xls R 300m Assamese

Developed by infinitejoy
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_7_0 dataset, designed for Assamese automatic speech recognition tasks.
Downloads 13
Release Time : 3/2/2022

Model Overview

This is an optimized automatic speech recognition model for Assamese, fine-tuned based on the XLS-R-300M architecture, suitable for speech-to-text tasks in Assamese.

Model Features

Assamese Optimization
Specially fine-tuned for Assamese, improving recognition accuracy for this language.
Based on XLS-R-300M
Uses the powerful XLS-R-300M architecture as the base model.
Trained on Common Voice Dataset
Trained on the mozilla-foundation/common_voice_7_0 dataset.

Model Capabilities

Assamese speech recognition
Audio-to-text conversion

Use Cases

Speech Transcription
Assamese Speech-to-Text
Convert Assamese speech content into text
WER: 72.64, CER: 27.35
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase