AIbase
EN
Home
Whisper Small Uzbek
W

Whisper Small Uzbek

Developed by abduaziz
Uzbek automatic speech recognition model fine-tuned from OpenAI Whisper-small on Common Voice 17.0 dataset
Speech Recognition
Transformers
 OtherOpen Source License:Apache-2.0#Uzbek speech recognition#Multi-dialect ASR#Low-resource language optimization
Downloads 20
Release Time : 12/14/2024

Model Overview

This model is an automatic speech recognition (ASR) model specifically optimized for Uzbek language, fine-tuned based on OpenAI's Whisper-small architecture, suitable for Uzbek speech-to-text tasks

Model Features

Uzbek Language Optimization
Specially fine-tuned for Uzbek language, showing better language adaptability compared to the original Whisper model
Efficient Training
Uses relatively small Whisper-small architecture to reduce computational resource requirements while maintaining performance
Public Dataset Training
Trained on Mozilla Common Voice 17.0 public dataset with reliable data sources

Model Capabilities

Uzbek speech recognition
Speech-to-text
Audio content transcription

Use Cases

Speech Transcription
Uzbek Speech Transcription
Convert Uzbek speech content into text
Word error rate 35.87%
Voice Assistant
Uzbek Voice Command Recognition
For command recognition in Uzbek voice assistant systems
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