Hacker News new | past | comments | ask | show | jobs | submit | sebastianvoelkl's comments login

Congrats

really cool. A while back I've build this database of 1000+ hand-selected educational YouTube videos, so I'm going to try out a few of them to put in this tool :) https://www.edutube.app/


This is awesome! Did you hand select all 1000? I wanted to hand select for the categories to get some better starting recommendations but it was taking too long so I was a bit lazy and just scripted it…


Yeah I literally hand-selected all of them to remain the quality of videos that I wanted


If you have a list of the IDs of the videos (and maybe categories) I can bulk add them! If you want to discuss a collab of some sort feel free to email me!


Nice


Thanks for letting people know where you live and how to find you more easily :)


This in the heart of the museum quarter, unlikely that anyone lives there. The only thing that is within a 500 radius of the exhibition and not a museum is the math department of the Ludwig Maximilian university. That is my guess where Sebastian is, but good luck finding him there.


I'm waiting for you


Hey HN, A few months ago I finished a side-project called edutube.app A platform to discover 1000+ educational YouTube videos. I put a lot of work into the project, but it failed (Didn't have a lot of paying customers), so from today on, EduTube is free to use for everyone. I hope you like it


The only thing Whisper misses is speaker diarization. I'm currently working on a model that uses Whisper + pyannote to transcribe Interviews and also detects who is speaking. It's working but damn it takes so long


Can you not separate into two phases? Speech separation to get source per speaker, and then whisper on each in isolation (maybe interlacing prompts)?



I'm badly looking for that! Is there a repo I can follow?


not GP (hoping he responds tho) but i've been collecting a couple of diarization options: https://github.com/sw-yx/ai-notes/blob/main/AUDIO.md

basically whisper.cpp has some support but its not great (based on my own testing)

- https://huggingface.co/spaces/vumichien/whisper-speaker-diar...

- https://github.com/Majdoddin/nlp pyannote diarization

- whisperX with diarization https://twitter.com/maxhbain/status/1619698716914622466 https://github.com/m-bain/whisperX


I can share my repo when it's finished. In the meantime, you can take a look at this: https://huggingface.co/spaces/vumichien/whisper-speaker-diar...


My goal for my project is to build a tool that transcribes Interviews (e.g, in Sales or Recruiting) and puts the Transcription through ChatGPT (Waiting for the API atm) to make a summary that looks like the notes of the call. Speaker diarization is important, so I don't have more than 4000 tokens input in ChatGPT. I will see how it goes, but if it's reliable enough (looks like it so far), it will save the time it takes to write meeting notes and rewrite them to send them to someone after the call (Hiring Managers etc.) Imagine a 10x Otter.ai or something like that.


Why are you waiting for the API? The OpenAI Playground has API examples you can copy paste. You can go over 4000 tokens if you have a business justification and payment method. You have access to most of their models even the new Codex ones

Edit: Looked at your link and I misunderstood. I think I understand you're waiting for the ChatGPT specific model now?


> You can go over 4000 tokens if you have a business justification and payment method.

That's incorrect


You are correct that I was incorrect. Thank you for correcting me. I misread their documentation. Sounds like they might increase the token limit in the future, but right now it's 4097 tokens shared with the prompt


Ha. I’m also doing something similar with a friend at https://www.paxo.ai. Funny that we all seemed to have an similar idea, all at once.


What did you build the landing page with?


from the source code <!DOCTYPE html><!-- This site was created in Webflow. https://www.webflow.com --><!--


I also started building the same thing. Crazy that something that used to be nearly impossible will soon be a "hello world" type project


Sounds interesting do you have a page


Ok. Our service is pretty fast. Also the M-Macs is really fast imo


whats your training rig like?


There is a own section of this on https://www.edutube.app


This is cool, I use https://limnology.co/en/languages/en/keywords to find new channels


I think the YouTube suggestions got worse over time. In 1-2 weeks I will launch www.EduTube.app a platform to discover hand picked educational YouTube videos for those who are interested in it


Will your platform be "making suggestions" after users watch any hand-picked content? How do you plan to monetize this?


Not making any suggestions. A couple of categories are free to watch and for a 20$ one time payment You can have access to everything


It's interesting to see how often BCI's are trending on HN


To everyone who is reading this, I'm hiring at On Deck (beondeck.com) We are are a 100% Remote company and will stay remote forever.

Contact me if you'd like to join: sebastian.volkl@beondeck.com


What roles are you hiring for?


https://beondeck.com/careers incl. senior engineering roles


On Deck (beondeck.com) | Multiple roles incl. Senior Product and Data Engineers | Full-time | 100% Remote company

Hey! At On Deck, we build communities that help people start and scale companies, help people join companies, and help people at companies succeed at their jobs.

At On Deck, Product teams are highly autonomous. You will own the decisions, roadmap, and success of your team. You can learn about how we work in our Product Engineering Team Playbook (https://tinyurl.com/yzhwuuum)

Last year we raised our Series A from Keith Rabois at Founders Fund and nearly 200 of the best operators and investors (including many of our community members).

Tech Stack: React, TypeScript, Node, GraphQL and Postgres and a lot of No-Code

Contact: sebastian.volkl@beondeck.com


Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: