W

Whisper Small Turkish Tr Best

Developed by erenfazlioglu
Turkish speech recognition model fine-tuned based on OpenAI Whisper-small, with a word error rate of 26.34%
Downloads 61
Release Time : 10/4/2023

Model Overview

This model is an optimized version of the Whisper-small architecture for Turkish, focusing on speech-to-text tasks and suitable for Turkish speech recognition scenarios.

Model Features

Low Word Error Rate
Achieves a word error rate of 26.34% on the target dataset, outperforming the base model.
Efficient Fine-tuning
Significantly improves recognition accuracy for the target language with just 4000 training steps.
Lightweight Architecture
Based on the Whisper-small architecture, balancing performance and computational efficiency.

Model Capabilities

Turkish speech recognition
Audio to text conversion
Long-form speech transcription

Use Cases

Speech Transcription
Turkish Meeting Minutes
Automatically generate text transcripts from Turkish meeting audio.
26.34% word error rate
Media Subtitle Generation
Automatically generate subtitles for Turkish video content.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase