Welcome to the Elpis ASR documentation!

Elpis is a tool which language workers with minimal computational experience can use to build their own speech recognition system for automatically transcribing audio.

Installing Elpis

• Installing Elpis on your computer
• Install Elpis on Google Cloud for Kaldi
• Install Elpis on Google Cloud with GPU

Elpis workshop

• Getting started
• Overview
• Setup
  • Get some training files
  • Start Elpis
• Transcription types
• About the steps
• Recordings
  • Add files
  • Select tiers
  • Prepare
• Pronunciation Dictionary
  • Letter to sound rules
  • Pronunciation
• Training sessions
  • Settings
  • Training
  • Results
• Making a new transcription
• More information about training files
• Preparing files
  • Preparing your existing transcriptions
  • Clean your transcriptions by looking through them and checking the following:
  • Audio
  • Examples

For developers

• Viewing Elpis training log file
• How to setup repositories to develop Elpis
• Building the Elpis Docker image
• Making a release
• Using the CLI Elpis Python API
• Using the CLI for Elpis GPU
• Handy GCP commands