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

Show HN: I made a free transcription service powered by Whisper AI

freesubtitles.ai

Post reply on HN
Print view View original

61–70 of 135 posts

Re: Show HN: I made a free transcription service powered by Whisper AI

#61

Post by mayeaux »

kkielhofner wrote: post #47
mayeaux wrote: post #43

Earlier quoted context omitted.

Hey, I know the feeling, I felt bad when I had my GPU just sitting there and it's just a little Vast server lol. If you want to use your hardware to run this software I'd be more than happy to help get it setup!

For what's it worth my approach has been running a tweaked whisper-asr-webservice[0] behind traefik behind Cloudflare. Traefik enables end to end SSL (with Cloudlare MITM, I know) and also helps put the brakes on a little so even legitimate traffic that makes it through Cloudflare gets handled optimally and gracefully. I could easily deploy your express + node code instead (and probably will anyway because I just lik…

Right on, looking forward to it! Yeah I saw that module and was planning to use it but I just wrote up an Express/Node implementation first and never really looked back. But looking forward to collabing I will await your issues, cheers!

Re: Show HN: I made a free transcription service powered by Whisper AI

#62

Post by kkielhofner »

jw1224 wrote: post #44

Free startup idea: Use Whisper with pyannote-audio[0]’s speaker diarization. Upload a recording, get back a multi-speaker annotated transcription. Make a JSON API and I’ll be your first customer. [0] https://github.com/pyannote/pyannote-audio

I think there's been talk to do speaker diarization with whisper-asr-webservice[0] which is also written in python and should be able to make use of goodies such as pyannote-audio, py-webrtcvad, etc.

Whisper is great but at the point we get to kludging various things together it might start to make more sense to use something like Nvidia NeMo[1] which was built with all of this in mind and more.

[0] - https://github.com/ahmetoner/whisper-asr-webservice

[1] - https://github.com/NVIDIA/NeMo

Re: Show HN: I made a free transcription service powered by Whisper AI

#63

Post by Namidairo »

Shouldn't the language and model inputs be dropdowns instead of text input?

I'm going to hope/assume you're doing some sort of sanitisation on those inputs.

Additionally, wouldn't you lose the language detection that's done for no language input? (IIRC, it uses the first 30 seconds to detect language if you don't specify one)

Re: Show HN: I made a free transcription service powered by Whisper AI

#65

Post by mayeaux »

Namidairo wrote: post #63

Shouldn't the language and model inputs be dropdowns instead of text input? I'm going to hope/assume you're doing some sort of sanitisation on those inputs. Additionally, wouldn't you lose the language detection that's done for no language input? (IIRC, it uses the first 30 seconds to detect language if you don't specify one)

Yeah someone submitted a PR for those to be fixed, I'm just wary about restarting the server because I haven't setup a way to be able to reboot without losing the websockets

Well those inputs should all error unless they are a valid value.

Yes if nothing is input it will automatically detect the language based on the first 30s of input

Re: Show HN: I made a free transcription service powered by Whisper AI

#66

Post by kkielhofner »

mayeaux wrote: post #17
giantg2 wrote: post #15

Earlier quoted context omitted.

Not even abuse, but just intensive use cases. Like the guy who posted a few says ago about recording and transcribing all day.

I setup the server to only transcribe two files at a time, so yeah someone could abuse it for sure with two big uploads and stick everyone else on the queue. But for me, even a 3 hour video translates with large model in about ~30 minutes so it wouldn't be too bad, but hopefully everyone is conscious to not do that, so far nobody has abused it which is cool.

Me again - why two at a time? In my initial testing with whisper-asr-webservice and my RTX 3090 I could pretty easily throw ~10 different files at it simultaneously as there is some natural staggering between API entry, CPU conversion/resampling/transcoding of audio, the actual audio length, network effects like upload speed, etc.

I also implemented some anti-abuse-ish features between traefik and Cloudflare that should help it stand up better in the face of bad actors abusing it.

Certainly not something to necessarily depend on but I thought I'd mention it.

Re: Show HN: I made a free transcription service powered by Whisper AI

#67

Post by pessimizer »

mayeaux wrote: post #28
pessimizer wrote: post #25

Earlier quoted context omitted.

Thanks a lot for this. I've wanted to test whisper's usefulness for vintage movie subtitling projects, but haven't had such a straightforward, preconfigured opportunity. I promise I'll beat the subs into some sort of shape as long as the timings are at least vaguely alright, and not waste your money.

Hey, glad I could be of use. The problem with Whisper is that it needs a lot of GPU. Actually my Mac can't even use my GPU so right away I had to get it up on a server, but Whisper is so powerful and it's so amazing that it's open source I am surprised nobody did this yet. I could see them charging for it but may as well use it anyways, the other services are insanely expensive ($10/h?!) and I don't really like their…

Nothing has come back from the two that I tried (one medium in French, the other large in Spanish), meaning no change on the page since I uploaded them an hour an a half ago. I loaded the page again in another tab, though, and after a few seconds "finishedProcessing" appeared under the form. I suspect that means something.

On Firefox 102.4.0esr, also uBlock Origin.

Re: Show HN: I made a free transcription service powered by Whisper AI

#68

Post by mayeaux »

password4321 wrote: post #58
coder543 wrote: post #50

Earlier quoted context omitted.

It's not as if people aren't trying to do that: https://github.com/openai/whisper/discussions/264 I tried out this notebook about a month ago, and it was rough . After spending an evening improving it, I got everything "working", but pyannote was not reliable. I tried it against an hour-ish audio sample, and I found no way to tune pyannote to keep track of ~10 speakers over the course of that audio. It would identify…

Speaker recognition is another piece that isn't usually as high a priority as recognizing the speech.

It's a new thing to me, I hadn't really considered it. Do they have that for movies and stuff? I can't think of a clear case when I've seen it

Re: Show HN: I made a free transcription service powered by Whisper AI

#69

Post by Namidairo »

mayeaux wrote: post #65
Namidairo wrote: post #63

Shouldn't the language and model inputs be dropdowns instead of text input? I'm going to hope/assume you're doing some sort of sanitisation on those inputs. Additionally, wouldn't you lose the language detection that's done for no language input? (IIRC, it uses the first 30 seconds to detect language if you don't specify one)

Yeah someone submitted a PR for those to be fixed, I'm just wary about restarting the server because I haven't setup a way to be able to reboot without losing the websockets Well those inputs should all error unless they are a valid value. Yes if nothing is input it will automatically detect the language based on the first 30s of input

I wasn't even aware that it was on GitHub, which I suppose is an issue in itself.

Re: Show HN: I made a free transcription service powered by Whisper AI

#70

Post by TheBrokenRail »

mayeaux wrote: post #65
Namidairo wrote: post #63

Shouldn't the language and model inputs be dropdowns instead of text input? I'm going to hope/assume you're doing some sort of sanitisation on those inputs. Additionally, wouldn't you lose the language detection that's done for no language input? (IIRC, it uses the first 30 seconds to detect language if you don't specify one)

Yeah someone submitted a PR for those to be fixed, I'm just wary about restarting the server because I haven't setup a way to be able to reboot without losing the websockets Well those inputs should all error unless they are a valid value. Yes if nothing is input it will automatically detect the language based on the first 30s of input

> I'm just wary about restarting the server because I haven't setup a way to be able to reboot without losing the websockets

Wait what. Not being able to safely restart the server sounds like a disaster waiting to happen.

Post reply on HN