/shadowing_learning

Use Speech to Text to divide native speaker audio in to sentences, so learners could repeat them

Primary LanguageRuby

Shadowing Learning

Getting Started

  • copy .env.example .env
  • docker compose run --rm web bin/rails db:prepare
  • Setup Google speech to text and place Service Account credentials to config/credentials.json

Usage

  • docker compose up
  • docker compose stop
  • IMPORTANT: input audios should be in WAV format, MONO channel, 16 kHz Sample Rate