smoores-dev / storyteller

Mirror of https://gitlab.com/smoores/storyteller
MIT License
27 stars 3 forks source link

Enhance EPUB 3 Creation Process and Model Flexibility #4

Open ashwinm4friends opened 3 months ago

ashwinm4friends commented 3 months ago

Hi,

Firstly, thank you for developing Storyteller! It's a fantastic tool for syncing audiobooks and ebooks.

I have a few suggestions to enhance the EPUB 3 creation process and provide more flexibility:

  1. Google Colab Notebook: The EPUB 3 creation process is quite compute-intensive. Could you provide a Google Colab notebook to help users offload this process to the cloud?

  2. Model Flexibility: It would be beneficial to allow users to specify models, such as the base.en Whisper model, for transcription. This would enable users to select models based on their performance needs and resource constraints.

  3. Faster-Whisper Transcription: Can we integrate Faster-Whisper for transcription? This would offer more flexibility and potentially improve performance.

  4. External Subtitle File Support: Can we allow the use of subtitle files (SRT or VTT) generated outside the Storyteller backend as inputs along with EPUB and MP3 files? This would provide more options for users who already have subtitles available.

Please let me know if you'd prefer these requests to be split into separate issues.

Thanks for considering these enhancements!

Device Information: