HackerTrans
TopNewTrendsCommentsPastAskShowJobs

znagengast

51 karmajoined 8 tahun yang lalu
@ZachNagengast

comments

znagengast
·4 hari yang lalu·discuss
Takes me back immediately, really cool!
znagengast
·3 bulan yang lalu·discuss
Maintainer of WhisperKit here, confirming we do exactly that for longform. We search for the longest "low energy" silence in the second half of the audio window and set the chunking point to the middle of that silence. It uses a version of the webrtc vad algorithm, and significantly speeds up longform because we can run a large amount of concurrent inference requests through CoreML's async prediction api. Whisper is also pretty smart with silent portions since the encoder will tell it if there are any words at all in the chunk, and simply stop predicting tokens after the prefill step - although you could save the ~100ms encoder run entirely with a good vad model, which our recently opensourced pyannote CoreML pipeline can do.
znagengast
·4 bulan yang lalu·discuss
Turns out third party actually gets priority for ANE
znagengast
·3 tahun yang lalu·discuss
I have to play devils advocate here because for every one of these cases, there is probably a dozen of similar stories where the ambitious new guy actually did nuke the system with a risky friday release and then logged off for the weekend xD
znagengast
·3 tahun yang lalu·discuss
Compared to how much progress the iPhone made from initial launch to now, the potential for this product line is very exciting.