W

Whisper Small Fr

Developed by mozilla-ai
This is a Whisper-small speech recognition model fine-tuned on French datasets, reducing the word error rate by 6.793 percentage points compared to the baseline model.
Downloads 30
Release Time : 2/27/2025

Model Overview

This model is a French fine-tuned version of OpenAI Whisper-small, specifically designed for French speech-to-text tasks, demonstrating excellent performance on the Common Voice French dataset.

Model Features

French Optimization
Specifically fine-tuned for French speech data, significantly improving French recognition accuracy.
Performance Improvement
Compared to the baseline model, the word error rate is reduced by 22.3%, and the loss value is reduced by 61.1%.
Lightweight
Based on the Whisper-small architecture, suitable for deployment in resource-limited environments.

Model Capabilities

French speech recognition
Speech-to-text
Audio transcription

Use Cases

Speech Transcription
French Meeting Minutes
Automatically convert French meeting recordings into text transcripts
Word error rate 23.511%
French Podcast Transcription
Convert French podcast content into searchable text
Assistive Technology
French Real-time Captions
Generate real-time captions for French video content
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase