W

Wav2vec2 Large Xlsr Punjabi

Developed by manandey
This is an automatic speech recognition (ASR) model fine-tuned on Punjabi speech data based on the facebook/wav2vec2-large-xlsr-53 model.
Downloads 20.46k
Release Time : 3/2/2022

Model Overview

This model is specifically designed for Punjabi speech recognition tasks, trained on the Common Voice dataset, and supports speech input with a 16kHz sampling rate.

Model Features

Punjabi Speech Recognition
Speech recognition capabilities optimized specifically for Punjabi
Based on XLSR Large Model
Fine-tuned on facebook's wav2vec2-large-xlsr-53 model, featuring powerful speech feature extraction capabilities
16kHz Sampling Rate Support
Supports processing speech input with a 16kHz sampling rate

Model Capabilities

Speech Recognition
Punjabi Speech-to-Text

Use Cases

Speech Transcription
Punjabi Speech Transcription
Convert Punjabi speech into text
Word Error Rate 57.31%
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase