D

Distil Large V3.5 Ct2

Developed by distil-whisper
Distil-Whisper is a distilled version of the Whisper model, achieving efficient speech recognition through large-scale pseudo-labeling technology
Downloads 264
Release Time : 3/14/2025

Model Overview

An efficient speech recognition model optimized through distillation of the Whisper model, converted to CTranslate2 format for faster inference speed

Model Features

Efficient Inference
Optimized with the CTranslate2 engine, offering faster inference speed compared to the original Whisper model
Knowledge Distillation
Distills knowledge from the Whisper model using large-scale pseudo-labeling technology while maintaining high accuracy
Hardware Adaptation
Supports both CPU and GPU operation, automatically selecting the optimal computation type (float16/float32)

Model Capabilities

English Speech Recognition
Audio File Transcription
Real-time Speech-to-Text

Use Cases

Speech Transcription
Meeting Minutes
Automatically convert meeting recordings into text transcripts
Podcast Transcription
Convert podcast audio content into searchable text
Assistive Tools
Subtitle Generation
Automatically generate English subtitles for video content
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase