bulk_transcribe_youtube_videos_from_playlist

AI

speech transcription

SHOW HN2023

125points
43comments
#503of 3,109 in 2023
Top 17%of 2023 by points

How HN took it

LovedMost comments that take a side are positive

6 positive, 7 neutral or asking, 0 mixed, 1 critical, out of 14 comments about the project. Thread score +0.26.

Idea: 3 for, 1 againstPerformance: 2 for, 0 againstExecution: 1 for, 0 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Whisper transcripts are more accurate than YouTube's auto-generated ones.

    From 3 comments
    • Whisper is generally better than the one in youtube.
      tsurba on HN
    • I found the YouTube one to be really bad for my voice and the way I speak - Whisper does it perfectly (using the large dataset). English is my second language, and I mumble.
      kawsper on HN
    • I would say that overall they are much, much better than the auto generated ones from YouTube. If the speaker speaks incredibly clearly and slowly, without slang, etc, then the…
      eigenvalue on HN
  • Well architected, and the spaCy integration is nice.

    From 1 comment
    • This is awesome man. We attempted to build something similar and wound up giving up and pivoting to transcripts w/ a punctuation model to enhance them. If this was around at the…
      skeptrune on HN

Objections

  • Speaker diarization is not solved in this tool.

    From 2 comments
    • You might want to look into diarization also http://gladia.io/ seem to be doing it well. It makes a great difference to have transcripts with speaker annotation.
      tehlike on HN
    • to zoom out a bit, this is known as the 'cocktail party problem' and is very much considered unsolved (particularly when there is an unknown number of speakers or overlapping…
      huac on HN
  • Setup is hard for non-Python users.

    From 1 comment
    • I don't have any experience with Python. Can someone point me to definitive (and idiot-proof) tutorials for Win 10 Pro and Mac OS? Maybe using Docker? I just don't know but am…
      chiefalchemist on HN

Requests

  • Add speaker diarization.

    From 2 comments
    • You might want to look into diarization also http://gladia.io/ seem to be doing it well. It makes a great difference to have transcripts with speaker annotation.
      tehlike on HN
    • > Turning those abstract speaker identifications into actual names would seem to require a fair bit of intelligence As someone looking for this functionality, this is the easiest…
      pavel_lishin on HN
  • Make it a Chrome extension.

    From 1 comment
    • This is nice! I like how you've built upon your previous youtube transcript cleaner project and put together something really compelling. Have you thought about spinning this…
      josephrmartinez on HN

Questions

  • How does it compare to YouTube's own transcripts?

    From 1 comment
    • Out of curiosity, how does it compare to YouTube’s own generated transcripts?
      barefeg on HN

Alternatives named

  • WhisperX

    From 1 comment
    • The whisperX project has most of it covered they are integrating the new v3 model waiting for a ccp GGUF version also there is a workaround for the latest speaker diarization but…
      jimmySixDOF on HN
  • Gladia

    From 1 comment
    • You might want to look into diarization also http://gladia.io/ seem to be doing it well. It makes a great difference to have transcripts with speaker annotation.
      tehlike on HN
  • Deepgram

    From 1 comment
    • Deepgram is really good and around your price point too. They also have $200 free credit which should be more than enough for most hobby protects.
      tornato7 on HN
  • YouTube auto-generated transcripts

    From 1 comment
    • Out of curiosity, how does it compare to YouTube’s own generated transcripts?
      barefeg on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/38236198)