AIbase
EN
Home
Wav2vec2 Large Xls R 300m Marathi Cv8
W

Wav2vec2 Large Xls R 300m Marathi Cv8

Developed by infinitejoy
This is an automatic speech recognition (ASR) model fine-tuned on the Marathi speech dataset based on Facebook's wav2vec2-xls-r-300m model.
Speech Recognition
Transformers
 OtherOpen Source License:Apache-2.0#Marathi Speech Recognition#Low-resource Language Processing#XLS-R Architecture
Downloads 443
Release Time : 3/2/2022

Model Overview

This model is specifically designed for Marathi speech recognition tasks, fine-tuned on the Common Voice 8 dataset, capable of converting Marathi speech into text.

Model Features

Multilingual Support
Based on the XLS-R architecture, it has the capability to handle multiple languages, with this version specifically optimized for Marathi.
Efficient Training
Uses mixed-precision training and the Adam optimizer for high training efficiency.
Robustness
Optimized for conversational scenarios and various speech events.

Model Capabilities

Marathi Speech Recognition
Speech-to-Text
Handling Conversational Speech

Use Cases

Speech Transcription
Marathi Speech Transcription
Convert Marathi speech content into text
Word Error Rate (WER) 55.716, Character Error Rate (CER) 13.842
Voice Assistants
Marathi Voice Command Recognition
Used to build voice assistants that support Marathi
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
EnglishįŽ€äŊ“中文įšéĢ”中文ãĢãģんご
Š 2025AIbase