W

Whisper Ja Anime V0.1

Developed by efwkjn
A Whisper variant model focused on speech recognition in the Japanese anime field, optimized for the characteristics of anime audio
Downloads 205
Release Time : 12/15/2024

Model Overview

A Japanese automatic speech recognition model based on the Whisper architecture, specifically optimized and trained for anime-related audio to reduce hallucination generation and improve transcription accuracy

Model Features

Optimized for the anime domain
Specifically trained for the characteristics of anime audio, performs better than general models on anime-related test sets
Anti-hallucination design
Reduce incorrect transcription and hallucination generation through training strategies
Flexible usage modes
Supports both timestamped and non-timestamped usage modes

Model Capabilities

Japanese speech transcription
Anime audio recognition
Long text processing
Timestamped transcription

Use Cases

Anime content production
Anime subtitle generation
Automatically generate Japanese subtitles for anime videos
The CER on the anime test set is lower than that of general models
Anime dialogue analysis
Used for content analysis and retrieval of anime dialogues
Game audio processing
Game speech transcription
Transcribe Japanese speech in games such as Genshin Impact and Honkai: Star Rail
Performs excellently on game test sets
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase