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

Show HN: Self-host Whisper As a Service with GUI and queueing

github.com

Post reply on HN
Print view View original

31–40 of 60 posts

Re: Show HN: Self-host Whisper As a Service with GUI and queueing

#31

Post by cjonas »

sebastianvoelkl wrote: post #22
sebastianvoelkl wrote: post #21

Earlier quoted context omitted.

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 tak…

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

Re: Show HN: Self-host Whisper As a Service with GUI and queueing

#32

Post by epoch_100 »

sebastianvoelkl wrote: post #22
sebastianvoelkl wrote: post #21

Earlier quoted context omitted.

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 tak…

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.

Re: Show HN: Self-host Whisper As a Service with GUI and queueing

#33

Post by binarymax »

deskamess wrote: post #29

Related/Off Topic: Is there a documented way to improve the accuracy of a particular language model? Say we can put in the effort to collect 1000's of verified/transcribed samples of a language that is currently scored poorly (WER). What steps do I have to take to get those improvements into the system?

Yes, you need to fine-tune the model with your data. This might be easy or hard, depending on your experience level and complexity of the model and available tooling.

For this model specifically (https://github.com/openai/whisper) it would be a significant challenge for a newcomer. Luckily Huggingface has a blog post that will get you started: https://huggingface.co/blog/fine-tune-whisper

Re: Show HN: Self-host Whisper As a Service with GUI and queueing

#34

Post by jalino23 »

sebastianvoelkl wrote: post #10

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

whats your training rig like?

Re: Show HN: Self-host Whisper As a Service with GUI and queueing

#36

Post by jotnguyen »

tikkun wrote: post #25
jotnguyen wrote: post #23

Earlier quoted context omitted.

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

Re: Show HN: Self-host Whisper As a Service with GUI and queueing

#39

Post by moneywoes »

sebastianvoelkl wrote: post #22
sebastianvoelkl wrote: post #21

Earlier quoted context omitted.

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 tak…

Sounds interesting do you have a page

Re: Show HN: Self-host Whisper As a Service with GUI and queueing

#40

Post by moneywoes »

epoch_100 wrote: post #32
sebastianvoelkl wrote: post #22

Earlier quoted context omitted.

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 tak…

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?
Post reply on HN