whisper-medium-ar Open-source Speech Recognition Model - Free Deployment for Precise Recognition of Arabic Speech

Home

Whisper Medium Ar

Developed by arbml

A speech recognition model fine-tuned on Arabic datasets based on openai/whisper-medium

Speech Recognition

Transformers

Open Source License:Apache-2.0 #Arabic Speech Recognition #Multi-dialect Support #Low Word Error Rate

Downloads 49

Release Time : 12/13/2022

Model Overview

This model is an Arabic fine-tuned version of Whisper Medium, specializing in Automatic Speech Recognition (ASR) tasks, supporting Arabic speech-to-text conversion

Model Features

Arabic Optimization

Specially fine-tuned for Arabic speech, improving recognition accuracy

Multi-dataset Validation

Validated on multiple Arabic datasets including Common Voice and FLEURS

Efficient Training

Utilizes mixed-precision training to optimize training efficiency

Model Capabilities

Arabic Speech Recognition

Speech-to-Text

Multi-accent Recognition

Use Cases

Speech Transcription

Arabic Speech Transcription

Convert Arabic speech content into text

Achieved a 12.04% word error rate on the FLEURS dataset

Voice Assistant

Arabic Voice Command Recognition

Used for voice command recognition in Arabic voice assistants or control systems

Property	Details
Name	Whisper Medium ar - Zaid Alyafeai
Results	Task: Automatic Speech Recognition Datasets: mozilla - foundation/common_voice_11_0 (test split, ar config): Wer = 34.28 google/fleurs (test split, ar_eg config): Wer = 12.04

Training Loss	Epoch	Step	Validation Loss	Wer
0.2963	0.1	1000	0.9115	27.3641
0.2676	0.2	2000	0.8796	24.1024
0.3166	0.3	3000	0.8467	20.1700
0.2797	0.4	4000	0.8756	29.4889
0.2302	0.5	5000	0.8523	19.6414
0.2803	0.6	6000	0.8715	19.7413
0.2794	0.7	7000	0.8548	18.6840
0.2173	0.8	8000	0.8543	17.9019
0.217	0.9	9000	0.8518	16.3840
0.1718	1.0	10000	0.8488	16.5882

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

Whisper Medium Ar

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 openai/whisper-medium

🚀 Quick Start

✨ Features

Datasets

Metrics

Tags

Model Index

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License