W

Wav2vec2 Large Xlsr Mr 2

Developed by gchhablani
This is an automatic speech recognition (ASR) model fine-tuned on Marathi based on the facebook/wav2vec2-large-xlsr-53 model, trained using partial data from the InterSpeech 2021 Marathi dataset.
Downloads 13
Release Time : 3/2/2022

Model Overview

This model is specifically designed for Marathi speech recognition tasks, capable of converting Marathi speech into text.

Model Features

High Accuracy Speech Recognition
Achieves 19.98% WER on the InterSpeech 2021 Marathi test set
Multi-Sample Rate Support
Supports 16kHz sample rate input and can process 8kHz audio through resampling
No Language Model Required
Can be used directly without additional language model support

Model Capabilities

Marathi speech recognition
Audio to text conversion
Speech content transcription

Use Cases

Speech Transcription
Marathi Speech Transcription
Convert Marathi speech content into text format
Achieves 19.98% word error rate on the test set
Voice Assistants
Marathi Voice Command Recognition
Used to understand Marathi voice commands
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase