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

Wav2vec2 Large Xls R 300m Odia Cv8

Developed by infinitejoy
An automatic speech recognition model fine-tuned on the Odia (OR) Common Voice dataset based on facebook/wav2vec2-xls-r-300m
Speech Recognition
Transformers
 OtherOpen Source License:Apache-2.0#Odia speech recognition#Multilingual support#Low-resource optimization
Downloads 16
Release Time : 3/2/2022

Model Overview

This is an optimized automatic speech recognition model for Odia, fine-tuned on the Common Voice 8.0 dataset

Model Features

Multilingual pre-training foundation
Based on Facebook's wav2vec2 XLS-R 300M multilingual pre-trained model with powerful speech feature extraction capabilities
Odia optimization
Specifically fine-tuned for Odia and trained on the Common Voice 8.0 Odia dataset
Relatively low word error rate
Achieves a word error rate (WER) of 0.5818 on the evaluation set, outperforming the base model

Model Capabilities

Odia speech-to-text
Automatic speech recognition
Speech content transcription

Use Cases

Speech transcription
Odia speech content transcription
Convert Odia speech content into text format
Word error rate 0.5818
Voice assistant
Odia voice command recognition
Used for understanding Odia voice commands
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