Curious if there was a benefit to using whisper over something like vosk which can transcribe on mobile device pretty decently.
Whisper has other interesting functionality but for straight transcription it seems a bit heavy. Still learning about it and putting it through its paces.
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?
This is cool. We have integrated Whisper with our human in the loop tech at Scribie [1] and the results have been great. We offer free credits if you want to try it out.
What is the maximum length of audio allowed? What are your costs in running this? Are the hardware requirements substantial?
Right now the limit is 100MB because of Cloudflare, no length limit, costs $1.30/h to run this, that's enough for a 2x RTX A6000 on Vast.ai can you check out the specs there
Recently I’ve been using my iPad as a transcription “keyboard” for my laptop when writing documents in Dropbox paper. Open the document on both computers, then use dictate to enter all text, and then correct if necessary with the laptop. I’m expecting to move to iPad only when I can use stage manager with an external monitor.
Dictation is also great when writing in a foreign language: I speak German ok-ish, writing is harder. Dictation helps writing more correct German.
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…
Thanks for sharing! I was looking for a M1 solution weeks ago snd couldn‘t find any working one. Will try that one now! Looking around for servers with GPUs etc. resulted in stopping me at playing around with it as i got overwhelmed with options.
Maybe I will put in some mechanism to prevent that but for now I just want to see if people could find it useful. I also have the code open source and will write tutorials for people to put up their own instance as well
It would be more useful if one could directly paste links to videos online as well. But yeah, in general this is extremely useful. I'm looking forward to video site integration. Would be great if youtube could finally retire their horrible auto caption function for something that actually works. Being able to easily watch media in different languages from around the world will be an absolute game changer.
Also, I have that tested (auto download) with YouTube-Dl, it works fine but haven't put it into the frontend, but may as well, it helps a lot on your own instance so you don't have to download it first and then upload it