Whisper Paper Explained: Robust Speech Recognition via Large-Scale Weak Supervision

Поділитися
Вставка
  • Опубліковано 16 лис 2024

КОМЕНТАРІ • 14

  • @vishalgoklani
    @vishalgoklani Рік тому +4

    A fine-tuning example would be awesome! btw, I extracted the audio from this UA-cam video and ran it through Whisper, it's not bad. Unfortunately I got back one giant blob of text. We need to use another LLM/transformer to rewrite the output into proper paragraphs, and also to summarize and remove extraneous content: "What is going on guys? Welcome back to another video. In this one, we're taking a " :)

  • @daniellewis6228
    @daniellewis6228 Рік тому

    You are one of the OGs. Thanks Aladdin.

  • @LoneRanger.801
    @LoneRanger.801 Рік тому

    New to your channel. I like that you go into the detail of the papers. Really looking forward to the fine tuning video next. Subscribed. 😊

  • @thomaschaigneau8187
    @thomaschaigneau8187 Рік тому

    Great video thanks!

  • @normalhuman6260
    @normalhuman6260 Рік тому

    Watching your Unet video. This one will be next in line. So much to learn in AI. I keep getting confused. How do you make a mind map of everything and organize all the info? Should explain in a video.

    • @AladdinPersson
      @AladdinPersson  Рік тому +2

      I need help with organizing what’s going in ML haha. My strategy is going bit deeper on most impactful papers and doing projects rather than trying to understand bit of everything, it’s simply too much

    • @normalhuman6260
      @normalhuman6260 Рік тому

      @@AladdinPersson Exactly. It makes me so nervous whenever I sit for an interview involving specialized applications. Everything I learn makes sense at that time but I get confused 3 months later. I am currently trying to make a mind map and will mail it to you if i am able to do a good job. Thanks for all the wonderful content

  • @MdAbdullahAlMashud
    @MdAbdullahAlMashud 7 місяців тому

    nice reading

  • @Janamejaya.Channegowda
    @Janamejaya.Channegowda Рік тому

    Thank you for sharing.

  • @aniketsingh249
    @aniketsingh249 Рік тому +1

    I have few question and ways to use whisper is there any community which talk about it

  • @gtg238s
    @gtg238s Рік тому

    Can you do a code and paper walk thru for continuous or binary hopfield pattern storage and recall

  • @ahmedgon1845
    @ahmedgon1845 Рік тому

    You are amazing keep going 👌👏

  • @champagnebulge1
    @champagnebulge1 3 місяці тому

    I can reach the point where Whisper transcribes a UA-cam vid, but I'm having trouble with the speaker identification or diarisation part. Anyone got a link to a great tutorial?

  • @normalhuman6260
    @normalhuman6260 Рік тому

    First? Lol