Welcome to KoSpeech’s documentation!

GETTING STARTED

• What’s New
• Note
• KoSpeech: Open-Source Toolkit for End-to-End Korean Speech Recognition [Paper]
• Supported Models
• Pre-processed Transcripts
• Introduction
• Roadmap
• Installation
• Get Started
• Troubleshoots and Contributing
• Citation
• KsponSpeech-preprocess

ARCHITECTURE

• Interface
• Deep Speech 2
• Listen, Attend and Spell
• RNN Transducer
• Speech Transformer
• Jasper
• Conformer
• Modules

LIBRARY REFERENCE

• Checkpoint
• Criterion
• Data
• Decode
• Evaluator
• Optim
• Learning Rate Scheduler
• Trainer
• Vocabs
• Etc