Created
May 20, 2024 13:38
-
-
Save alexfazio/f862ace214c5239ac00930e89dd4b57c to your computer and use it in GitHub Desktop.
supplement-todo
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # TODO: Add Youtube download module | |
| # TODO: Remember to download the .srt file and transcript from YouTube when you download the video. | |
| # TODO: Verify if it's possible to download the transcript without timings from YouTube. | |
| # TODO: refactor the names of modules | |
| # TODO: Please confirm why an unnecessary .srt file, containing all the subtitles, is being generated in the crew_output. | |
| # TODO: Add a script module to clean the contents of api_response.json after each run. This will help prevent conflicts or errors during the next execution. | |
| # TODO: Add a caption maker in the style of @tsarnick. You may need to input the speaker's name. | |
| # TODO: change subtitle style & format | |
| # TODO: if subtitler.py find existing output, it should overwrite it | |
| # TODO: Improve the speed of Whisper | |
| # TODO: check if unnecessary codec conversions might be taking place | |
| # TODO: subtitler should only operate on files with matching titles | |
| # TODO: set a warning if video is longer than 15 mins | |
| # TODO: add predicted token and cost expense (measurability) | |
| # TODO: extract .mp3 from .mp4 before passing it to whisper, to make it faster |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment