Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OTranscribe: A free and open tool for transcribing audio interviews

otranscribe.com

Post reply on HN
Print view View original

31–40 of 109 posts

Re: OTranscribe: A free and open tool for transcribing audio interviews

#31

Post by stavros »

Zambyte wrote: post #30
stavros wrote: post #28

Earlier quoted context omitted.

What's OpenAI Whisper vs whisper.cpp? Do you mean whisper-diarization uses the API?

https://github.com/openai/whisper vs https://github.com/ggerganov/whisper.cpp They are two inference engines for running the whisper ASR model, each with their own API AFAIK.

Ah I see, thanks. Hm, I would imagine that it's not hard to make something that works with both (the surface area of the API should be fairly small, I imagine), odd that projects use the former and not the latter.

Re: OTranscribe: A free and open tool for transcribing audio interviews

#32

Post by stavros »

TrojanHookworm wrote: post #3

Use this a lot. It's nice and simple and has exactly the tools you need (playback speed control, easy pause/play) and nothing more. Greatly prefer it over automatic transcription tools give you 40 pages of 'umm's and 'ahhhh's to filter through and edit.

Can you not give the transcript to an LLM to remove the umms and ahhs?

Re: OTranscribe: A free and open tool for transcribing audio interviews

#33

Post by dmitrykan »

I'm working on the tool, that includes AI. My original target is to test it on my https://www.youtube.com/c/VectorPodcast by offering something that Lex Fridman does for his episodes.

Current features: 1. Download from YT 2. Transcribe using Vosk (output has time codes included) 3. Speaker diarization using pyannote - this isn't perfect and needs a bit more ironing out.

What needs to be done: 4. Store the transcription in a search engine (can include vectors) 5. Implement a webapp

If anyone here is interested to join forces, let me know.

Re: OTranscribe: A free and open tool for transcribing audio interviews

#36

Post by jrochkind1 »

Kinda surprised to not have AI integration.

You do still need to proof and QA even AI results, if you want a publication quality result, and do things like attribute who is speaking when (at least Whisper can't do that), and correct "unusual" last names and things. So I feel like people using AI still need good tools for the correcting/finishing/proofing too, that would be similar to the tools for non-assisted transcription.

Re: OTranscribe: A free and open tool for transcribing audio interviews

#37

Post by BiteCode_dev »

stavros wrote: post #32
TrojanHookworm wrote: post #3

Use this a lot. It's nice and simple and has exactly the tools you need (playback speed control, easy pause/play) and nothing more. Greatly prefer it over automatic transcription tools give you 40 pages of 'umm's and 'ahhhh's to filter through and edit.

Can you not give the transcript to an LLM to remove the umms and ahhs?

People not used to AI have blind spots that prevent them from seing evident use case like this.

I'm always surprised at the amazed look of my friends when they see me concretely use the tool. They just didn't picture it until they saw it in action.

Re: OTranscribe: A free and open tool for transcribing audio interviews

#39

Post by stavros »

BiteCode_dev wrote: post #37
stavros wrote: post #32

Earlier quoted context omitted.

Can you not give the transcript to an LLM to remove the umms and ahhs?

People not used to AI have blind spots that prevent them from seing evident use case like this. I'm always surprised at the amazed look of my friends when they see me concretely use the tool. They just didn't picture it until they saw it in action.

It's not even people not used to AI, I developed a tool that uses AI to do something, and then kind of couldn't be bothered to fix some of the output manually. It only occurred to me days later that I can ask the AI to fix it.

Re: OTranscribe: A free and open tool for transcribing audio interviews

#40

Post by MattieTK »

jrochkind1 wrote: post #36

Kinda surprised to not have AI integration. You do still need to proof and QA even AI results, if you want a publication quality result, and do things like attribute who is speaking when (at least Whisper can't do that), and correct "unusual" last names and things. So I feel like people using AI still need good tools for the correcting/finishing/proofing too, that would be similar to the tools for non-assisted transc…

This was written a really long time ago by a former WSJ Graphics reporter (Elliot Bentley) who is now at Datawrapper.

It is now operated by Muckrock and hasn't seen changes made to it in a while.

That's why it doesn't have any of these integrations, the technology just didn't exist.

Post reply on HN