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

111–120 of 135 posts

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

#111

Post by andrew3726 »

ivalm wrote: post #91
kkielhofner wrote: post #55

Earlier quoted context omitted.

When it all comes together it's kind of a nightmare for an ASR model. There were plenty of times in reviewing the recordings and ASR output where I'd listen to the audio and have no idea what they said. I'm not sure which contributes most but I know from my prior experiences with ASR for telephony even clean speech on pristine connections does much worse with models trained on 16 kHz being fed native 8 kHz audio that…

Could one train an interpolation layer (eg take a bunch of 16k audio, down sample to 8k, train 8k->16k upsampler)? Or better yet (but more expensive), take whisper, freeze it, and train the upsampler on whisper’s loss.

Sure, that's called audio super resolution, there's a few papers/projects doing that. Haven't really seen models which are robust and have good generalization though.

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

#112

Post by Void_ »

I’m sorry to self promote again - but: https://whispermemos.com

I’m in love with the idea of pressing button on my Lock Screen and getting a perfect transcription in my inbox.

Also, just added emoji summarization in email subject, a small visual reminder of what your memo was about.

I hope this is useful to someone!

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

#113

Post by fire »

Void_ wrote: post #112

I’m sorry to self promote again - but: https://whispermemos.com I’m in love with the idea of pressing button on my Lock Screen and getting a perfect transcription in my inbox. Also, just added emoji summarization in email subject, a small visual reminder of what your memo was about. I hope this is useful to someone!

is the app open source? I'm on android, so :c

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

#114

Post by IanCal »

kkielhofner wrote: post #59
gamegoblin wrote: post #53

Earlier quoted context omitted.

Yes, large was by far the best, but still not accurate enough that I'd be willing to put it into a fully automated pipeline. It would have gotten it right probably 75% of the time. Anything other than the large model was far too bad to even think about using.

What was the performance, resource usage, etc of doing this with large? What's the speed like? I'm still getting spun up on this but base delivers a pretty impressive 5-20x realtime on my RTX 3090. I haven't gotten around to trying the larger models and with only 24GB of VRAM I'm not sure what kind of success I'll have anyway... In my case the goal was to actually generate tweets based on XYZ. As I've already said th…

You can run the larger models just fine on a 3090. Large takes about 10G for transcribing English.

For a 1:17 file it takes:

6s for base.en, I think 2s to load the model based on the sound of my power supply.

33s for large, I think 11s of which is loading the model.

Varies a lot with how dense the audio file is, this was me giving a talk so not the fastest and quite clean audio.

While I saw near perfect or perfect performance on many things with smaller models, the largest really are better . I'll upload a gist in a but with Rap God passed through base.en and large.

edit -

Timings (explicitly marked as language en and task transcribe):

base.en => 23s

large => 2m50

Audio length 6m10

Results (nsfw, it's Rap God by Eminem): https://gist.github.com/IanCal/c3f9bcf91a79c43223ec59a56569c...

Base model does well, given that it's a rap. Large model just does incredibly, imo. Audio is very clear, but it does have music too.

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

#115

Post by smallerfish »

I've been testing whisper on AWS - the g4dn machines are the sweet spot of price/performance. It's extremely good, and there will be rapid consolidation in the transcription market as a result of it existing (its one major missing feature is the ability to supply custom dictionaries). The fact that it does a credible job at translation to english is a cherry on top.

Anyway, I'd love to get it running well on g5g, but they seem extremely temperamental. If anybody has, please let me know your secret. :)

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

#116

Post by smallerfish »

krick wrote: post #72

I didn't manage to transcribe anything (it just doesn't remember that I submitted anything), but whatever, I didn't need to anyway. I just wanted to ask: how good is Whisper with non-english? At least "major" ones, like, German, French, Russian, Spanish?

Spanish is great.

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

#117

Post by emadda »

n8cpdx wrote: post #95

This is a cool project. I’ve been very happy with whisper as an alternative to otter; it works better and solves real problems for me. I feel compelled to point out whisper.cpp. It may be cheaper for the author but is relevant for others. I was running whisper on a gtx 1070 to get decent performance; it was terribly slow on M1 Mac. Whisper.cpp has comparable performance to the 1070 while running on M1 CPU. It is easy…

How long would whisper.cpp take to transcribe 2 hours of audio on M1?

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

#118

Post by KevinBenSmith »

seligman99 wrote: post #74

It broke when I tried to feed it an entire podcast file, but still, I took this as a push to try out Whisper AI for myself, turns out it's easier to use than I thought. Long story short, I used it to transcriptify a podcast: https://scotts-podcasts.s3.amazonaws.com/temp/whisper/Intern... Not sure if there's a use for this that's not me, but I like the idea of having subtitles for a podcast I'm listening to.

In that case you could have a look at the Snipd podcast app. They have Whisper built in :)

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

#119

Post by kevinak »

emadda wrote: post #117
n8cpdx wrote: post #95

This is a cool project. I’ve been very happy with whisper as an alternative to otter; it works better and solves real problems for me. I feel compelled to point out whisper.cpp. It may be cheaper for the author but is relevant for others. I was running whisper on a gtx 1070 to get decent performance; it was terribly slow on M1 Mac. Whisper.cpp has comparable performance to the 1070 while running on M1 CPU. It is easy…

How long would whisper.cpp take to transcribe 2 hours of audio on M1?

Not sure about M1, but on the Macbook Pro 14" with an M1 Max using 8 threads I transcribed a 44 minute podcast in 16 minutes. So about 3x "real time" speed.

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

#120

Post by seligman99 »

JanSt wrote: post #97
seligman99 wrote: post #74

It broke when I tried to feed it an entire podcast file, but still, I took this as a push to try out Whisper AI for myself, turns out it's easier to use than I thought. Long story short, I used it to transcriptify a podcast: https://scotts-podcasts.s3.amazonaws.com/temp/whisper/Intern... Not sure if there's a use for this that's not me, but I like the idea of having subtitles for a podcast I'm listening to.

What tool did you use for the player-text presentation?

Mostly just vanilla JS on that page, and a tiny bit of Python glue code to turn the WebVTT output from Whisper into a data format for the JS.
Post reply on HN