https://github.com/ma-graff/pod-to-anki

A tool designed for language learners to transcribe podcast audio, analyze word/phrase frequencies, and generate flashcards for Anki.
https://github.com/ma-graff/pod-to-anki

anki language-learning podcast

Last synced: about 1 month ago
JSON representation

A tool designed for language learners to transcribe podcast audio, analyze word/phrase frequencies, and generate flashcards for Anki.

• Host: GitHub
• URL: https://github.com/ma-graff/pod-to-anki
• Owner: ma-graff
• Created: 2024-11-16T20:57:52.000Z (about 2 months ago)
• Default Branch: main
• Last Pushed: 2024-11-25T18:07:47.000Z (about 2 months ago)
• Last Synced: 2024-11-25T19:20:48.742Z (about 2 months ago)
• Topics: anki, language-learning, podcast
• Language: Python
• Homepage:
• Size: 2.85 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Pod to Anki

## Summary

A tool designed for language learners to transcribe podcast audio, analyze word/phrase frequencies, and generate flashcards for Anki.

## Project Status

### Next Steps

The next steps for the project include:

1. **Finishing Base Features**:

    - Transcribe, rank (non-basic) words/phrases, generate TTS/fetch audio, convert to anki

2. **Implementing Anki Functionality**: Export to Anki easily.

3. **User Interface**: Develop a user-friendly interface for easier interaction with the tool. Possibly self-hosted, docker or just tkinter.

4. **Documentation**: Improve and expand the project documentation

5. **Extended Features** to be implemented later:

    - Create a better UI, host on some service.

## Tools Used

**Libraries:**

OpenAI Whisper (for transcription)

scikit-learn (for TF-IDF computation)

deep-translator (for translation)

pypandoc (for document conversion)

collections (native, for word frequency analysis)

Python 3.8+

```pip install whisper scikit-learn deep-translator pypandoc```