W

Whisper Small Vi

Developed by namphungdn134
An automatic speech recognition model fine-tuned on Vietnamese speech data based on openai/whisper-small, improving Vietnamese transcription accuracy and robustness
Downloads 334
Release Time : 4/13/2025

Model Overview

An automatic speech recognition (ASR) model optimized for Vietnamese, suitable for speech-to-text tasks, with special optimization for Vietnamese accents and dialects

Model Features

Vietnamese optimization
Specially fine-tuned for Vietnamese speech characteristics, enhancing dialect and accent recognition capabilities
Lightweight model
Based on the Whisper small architecture, it reduces computational resource requirements while maintaining high accuracy
High-quality transcription
Achieves a word error rate (WER) of 9.3485 on test sets, demonstrating excellent performance

Model Capabilities

Vietnamese speech recognition
Audio-to-text conversion
Speech transcription

Use Cases

Speech transcription
Meeting minutes
Automatically transcribe Vietnamese meeting recordings into text records
Accuracy exceeds 90%
Media subtitle generation
Automatically generate subtitles for Vietnamese video content
Voice assistant
Vietnamese voice command recognition
Used for Vietnamese smart home or device control
Featured Recommended AI Models
ยฉ 2025AIbase