W

Wav2vec2 Xls R Pa IN A1

Developed by DrishtiSharma
An automatic speech recognition model fine-tuned on the Common Voice 8.0 Punjabi (India) dataset based on Facebook's wav2vec2-xls-r-300m model
Downloads 20
Release Time : 3/2/2022

Model Overview

This model is specifically designed for speech recognition tasks in Punjabi (Indian dialect), capable of converting speech to text

Model Features

High-precision recognition
Achieves a word error rate (WER) of 0.4908 on the evaluation set
Large-scale pre-training
Fine-tuned based on Facebook's wav2vec2-xls-r-300m model with powerful speech feature extraction capabilities
Language-specific optimization
Specially optimized for Punjabi (Indian dialect)

Model Capabilities

Speech-to-text
Punjabi (India) speech recognition
Real-time speech processing

Use Cases

Speech transcription
Voice memo transcription
Convert Punjabi (India) voice memos into searchable text
Approximately 51% accuracy (WER 0.4908)
Assistive technology
Voice-controlled applications
Voice control interfaces developed for Punjabi users
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase