Put very simply, Apple’s chip engineers were extremely motivated to eke out even more performance from their graphics subsystem-and found that the way memory was traditionally allocated was inefficient. There’s also a big new feature Apple is calling Dynamic Caching. Jason’s explanation of how it works is excellent: A lot of specs were thrown around by the company yesterday, but a software feature called Dynamic Caching really stood out because it’s clear that Apple is doing all it can to squeeze every bit of performance out of its GPUs. Jason Snell of Six Colors got a sneak peek at the new Macs announced at yesterday’s Scary Fast Apple event. Audio Hijack recorded both and started transcribing the audio as I was still recording. I spoke into my microphone, which was one source, and used the piano music from Zoom’s settings as the other source. ![]() We weren’t recording any shows today, so to test the new feature, I copied our MacStories Unwind recording session and used the Zoom audio settings as a stand-in for Federico. It’s using the same underlying Whisper technology as other apps, but by reducing transcription to part of your existing recording flow, it’s possible to transcribe on the fly as you record and identify speakers whose audio is coming from separate channels. The new block is a beta feature that Rogue Amoeba’s Paul Kafasis says the company will continue to refine. ![]() However, the most promising option so far is a new Transcribe block released today as part of Audio Hijack by Rogue Amoeba. ![]() There are dedicated apps to transcribe using Whisper like MacWhisper by Jordi Brun and Transcriptionist from the makers of Ferrite, both of which I’ve tried. Whisper isn’t perfect, but it does a remarkably good job, substantially lowering the effort and cost of generating transcripts. I’ve been playing around a lot with OpenAI’s Whisper speech-to-text engine this year.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |