W

Whisper Tiny

Developed by openai
Whisper Tiny is an automatic speech recognition (ASR) model developed by OpenAI, the smallest version in the Whisper series with 39M parameters.
Downloads 328.82k
Release Time : 9/26/2022

Model Overview

Whisper is a Transformer-based encoder-decoder model for automatic speech recognition and speech translation tasks. The model was trained on 680,000 hours of labeled speech data, demonstrating strong generalization capabilities.

Model Features

Large-scale Weakly Supervised Training
Trained on 680,000 hours of labeled speech data with strong generalization capabilities
Multilingual Support
Supports speech recognition and translation tasks in multiple languages
No Fine-tuning Required
Performs well on many datasets and domains without requiring fine-tuning
Lightweight Model
The Tiny version has only 39M parameters, suitable for resource-constrained environments

Model Capabilities

Speech recognition
Speech translation
Multilingual processing

Use Cases

Speech Transcription
Meeting Minutes
Automatically transcribe meeting recordings into text records
Achieves WER of 7.54 (clean) and 17.15 (other) on the LibriSpeech test set
Podcast Transcription
Transcribe podcast content into searchable text
Speech Translation
Real-time Translation
Translate speech from one language into text of another language in real-time
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase