whisper-tiny-ft-marathi-numbers Open-source Model - Free Realization of Marathi Number Audio Classification

Whisper Tiny Ft Marathi Numbers

Developed by sanchit-gandhi

This model is a fine-tuned version of openai/whisper-tiny on a Marathi digit dataset, specifically designed for audio classification tasks of Marathi digits.

Audio Classification

Transformers

Open Source License:Apache-2.0 #Marathi digit recognition #High-accuracy audio classification #Fine-tuned Whisper model

Downloads 13

Release Time : 3/24/2023

Model Overview

This is a fine-tuned Whisper model focused on audio classification tasks for Marathi digits, achieving an outstanding accuracy of 1.0 on the evaluation set.

Model Features

High accuracy

Achieves 1.0 accuracy on Marathi digit classification tasks

Lightweight

Based on Whisper-tiny architecture, suitable for resource-constrained environments

Domain-specific optimization

Specifically fine-tuned for Marathi digit recognition

Model Capabilities

Marathi digit recognition

Audio classification

Use Cases

Speech recognition

Marathi digit voice input system

Used to recognize spoken Marathi digits from users

Accuracy 1.0

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0002	1.0	128	0.7066	0.9990
0.0895	2.0	256	0.0764	0.9990
0.0281	3.0	384	0.0270	1.0
0.0191	4.0	512	0.0186	1.0
0.017	5.0	640	0.0166	1.0

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 Tiny Ft Marathi Numbers

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 whisper-tiny-ft-marathi-numbers

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

🔧 Technical Details

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License