AIbase
EN
Home
Whisper Small Dv
W

Whisper Small Dv

Developed by voxxer
A Dhivehi (official language of Maldives) automatic speech recognition model fine-tuned based on OpenAI Whisper-small, trained on Common Voice 13 dataset
Speech Recognition
Transformers
 OtherOpen Source License:Apache-2.0#Dhivehi speech recognition#Low word error rate#Small-scale fine-tuning
Downloads 21
Release Time : 8/15/2023

Model Overview

This is an automatic speech recognition (ASR) model optimized for Dhivehi, fine-tuned based on Whisper-small architecture, suitable for Dhivehi speech-to-text tasks

Model Features

Dhivehi optimization
Specially fine-tuned for Dhivehi, outperforming the original Whisper model in this language
Low word error rate
Achieved 13.1% word error rate (WER) on Common Voice 13 test set
Lightweight model
Based on Whisper-small architecture, balancing performance and computational resource requirements

Model Capabilities

Dhivehi speech recognition
Speech-to-text
Audio transcription

Use Cases

Speech transcription
Dhivehi meeting minutes
Automatically convert Dhivehi meeting recordings into text transcripts
Approximately 87% accuracy (WER 13.1%)
Voice assistant
Speech recognition module for Dhivehi voice assistant systems
Education
Language learning aid
Help learners practice Dhivehi pronunciation and get instant feedback
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
EnglishįŽ€äŊ“中文įšéĢ”中文ãĢãģんご
Š 2025AIbase