News for hackers. Stuff that matters.
Re:Whisper – open source speech recognition by OpenAI by eatsyourtacos on Wednesday September 21, 2022 @03:22PM (#32930158)
Can this be used as a real-time transcription or is it too slow for that?

Curious what anyone is using these days for a real-time transcription. It doesn't have to be perfect, but just good enough.

My kids watch some youtube vidoes where people will make a mod where it converts them talking to text then look for keywords and spawn a boss in Terraria if you say the wrong keyword etc.

I made a clone of that with the .NET System.Speech.Recognition library. It... works.. but my biggest problem is that #1 it waits until you are done speaking to translate to text on the callback, so there was too much of a delay for it to be fun.. the point is that it will be checking a stream of chatter. #2 is the recognition is pretty crap, I mean it's nearly good enough for my silly purpose but it's still pretty bad.

Re:Whisper – open source speech recognition by OpenAI by NaturalPhallacy on Wednesday September 21, 2022 @08:49PM (#32933559)
I tried it out and it's way too slow on my machine that is no slouch (Ryzen 9 5950/GTX 3080).

It's doing seconds of translation per minute for me at least.

Re:Whisper – open source speech recognition by OpenAI by whimsicalism on Wednesday September 21, 2022 @04:21PM (#32930998)
It might require too much work for what you are looking for, but the wav2letter library is the best real-time transcription OSS I have found by a considerable margin.
Re:Whisper – open source speech recognition by OpenAI by davidzweig on Wednesday September 21, 2022 @05:25PM (#32931705)
Out of interest, did you try Nemo? https://github.com/NVIDIA/NeMo
Re:Whisper – open source speech recognition by OpenAI by whimsicalism on Wednesday September 21, 2022 @05:32PM (#32931781)
No. I dont think it had streaming capabilities when i was doing this test two years ago, although i see it does now.
Re:Whisper – open source speech recognition by OpenAI by blueberrychpstx on Wednesday September 21, 2022 @03:33PM (#32930336)
If your family uses Apple devices, Apple offers free on-device speech recognition. Only caveat is that it needs to be restarted every minute due to whatever stupid limitation (or bug) they've introduced.

https://developer.apple.com/documentation/speech/recognizing...

Also, see `requiresOnDeviceRecognition`

Re:Whisper – open source speech recognition by OpenAI by TaylorAlexander on Wednesday September 21, 2022 @06:16PM (#32932298)
The base model seems to run faster than real time on my machine. The “medium” model is larger and runs more slowly - roughly real time or maybe slightly slower.
Re:Whisper – open source speech recognition by OpenAI by nshm on Wednesday September 21, 2022 @06:10PM (#32932235)
Re:Whisper – open source speech recognition by OpenAI by jayavanth on Wednesday September 21, 2022 @09:26PM (#32933802)
Re:Whisper – open source speech recognition by OpenAI by suyash on Wednesday September 21, 2022 @03:28PM (#32930267)
Depends if you're trying to run it offline or over the cloud.