Open-source wav2vec2-xls-r-60 Urdu speech recognition model - accurately recognize Urdu speech content

Wav2vec2 Xls R 60 Urdu

Developed by Maniac

This model is an automatic speech recognition model fine-tuned on the Common Voice Urdu dataset based on facebook/wav2vec2-large-xlsr-53

Speech Recognition

Transformers

OtherOpen Source License:Apache-2.0 #Urdu ASR #Low-resource speech recognition #Common Voice fine-tuning

Downloads 16

Release Time : 3/2/2022

Model Overview

Automatic speech recognition model for Urdu speech-to-text tasks, based on the wav2vec2 architecture

Model Features

High-precision Urdu recognition

Fine-tuned on the Common Voice Urdu dataset, optimized for Urdu speech

Based on wav2vec2 architecture

Uses facebook's wav2vec2-large-xlsr-53 pre-trained model as the foundation

Open-source license

Licensed under Apache 2.0, allowing both commercial and research use

Model Capabilities

Urdu speech recognition

Speech-to-text

Audio content transcription

Use Cases

Speech transcription

Urdu speech-to-text

Convert Urdu speech content into text format

Word Error Rate (WER) 0.9852

Voice assistants

Urdu voice interaction

Provides speech recognition capabilities for Urdu voice assistants

Training Loss	Epoch	Step	Validation Loss	Wer
1.468	166.67	500	3.0262	1.0035
0.0572	333.33	1000	3.5352	0.9721
0.0209	500.0	1500	3.7266	0.9834
0.0092	666.67	2000	3.8433	0.9852

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

Wav2vec2 Xls R 60 Urdu

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 Automatic Speech Recognition Model

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

🔧 Technical Details

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License