AIbase
EN
Home
Whisper Small Turkish V2
W

Whisper Small Turkish V2

Developed by atakanince
A speech recognition model fine-tuned on the Turkish Common Voice dataset based on OpenAI Whisper-small
Speech Recognition
Transformers
 OtherOpen Source License:Apache-2.0#Turkish Speech Recognition#Low Word Error Rate#Whisper Architecture
Downloads 61
Release Time : 3/3/2024

Model Overview

This model is a Turkish fine-tuned version of OpenAI Whisper-small, focusing on Turkish automatic speech recognition tasks, achieving a 20.4% word error rate on the Common Voice 16.1 Turkish test set.

Model Features

Turkish Optimization
Specially fine-tuned for Turkish, offering better performance in Turkish recognition compared to the original Whisper-small model
Lightweight Model
Based on the Whisper-small architecture, it maintains good performance while having a smaller model size
Open Source License
Uses Apache 2.0 license, allowing commercial and research use

Model Capabilities

Turkish Speech Recognition
Speech-to-Text
Audio Transcription

Use Cases

Speech Transcription
Turkish Meeting Minutes
Automatically transcribe Turkish meeting recordings into text records
Word error rate approximately 20.4%
Media Subtitle Generation
Automatically generate subtitles for Turkish video content
Voice Assistants
Turkish Voice Command Recognition
Used for understanding voice commands in Turkish 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