Launch Week Day 5: Introducing Reachability for PHP.Learn More
Socket
Book a DemoSign in
Socket

efficient-speech/lite-whisper-large-v3-turbo-fast

Package Overview
Dependencies
Contributors
3
Versions
6
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

efficient-speech/lite-whisper-large-v3-turbo-fast

Hugging FaceHugging Face Hub
Version
012024e
Version published
Monthly downloads
32
Contributors
3
Source

Model Card for Lite-Whisper large-v3-turbo-fast

Lite-Whisper is a compressed version of OpenAI Whisper with LiteASR. See our GitHub repository and paper for details.

Benchmark Results

Following is the average word error rate (WER) evaluated on the ESB datasets:

ModelAverage WER (↓)Encoder SizeDecoder Size
whisper-large-v310.1635M907M
lite-whisper-large-v3-acc10.1429M907M
lite-whisper-large-v310.2377M907M
lite-whisper-large-v3-fast11.3308M907M
    
whisper-large-v3-turbo10.1635M172M
lite-whisper-large-v3-turbo-acc10.2421M172M
lite-whisper-large-v3-turbo12.6374M172M
lite-whisper-large-v3-turbo-fast20.1313M172M
    
whisper-medium14.8306M457M

FAQs

Package last updated on 26 Feb 2025

Did you know?

Socket

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Install

Related posts