61–70 of 251 posts
this is amazing. if i had a mac i would try to reverse engineer the code, extract the weights and port it to something that works on linux/windows like torch or burn. then put the code on github and weights on a torrent site. lifes too short to let apple keep their models exclusive.
Aside from the legality of it, I think you are underestimating how complex it can be to do that. It is possible in theory but not something that will be a fun side quest like you are making it seem.
Earlier quoted context omitted.
For multilingual and noisy audio the best right now is MOSS-Transcribe-Diarize which was released just a few days ago Superwhisper does a lot more than just provide a whisper/parakeet UI so I’m not sure Apple will destroy them so easily
Thanks, was looking at a better diarization model. Even for those sorts of apps, MacParakeet which I've been using is FOSS so no payment needed. In reality these days with AI the ability to spin up a free and/or OSS competitor falls to zero.
A new VAD I found though is FireRedVAD which has better benchmark results than TEN and Silero by far
Earlier quoted context omitted.
There's tons, Parakeet was the last I remember seeing which seemed to gain traction (independent lightweight implementations etc).
I have tried everything (that will run on a 12GB RTX 4070) and I have yet to find anything with better accuracy than Whisper V2 Large for my dataset (discord audio from TTRPG sessions, isolated per-speaker, mostly non-American accents)
Whisper is the wrong model to benchmark against, or rather, there are better models that are state of the art now like Nemotron and Parakeet both by Nvidia, as well as Mistral's Voxtral and Cohere Transcribe. However, what's funny is, RIP to a lot of the paid apps that simply wrap Whisper, I'm sure Apple will make a native GUI such as a recorder app for macOS that obviates the need for these wrappers, which everyone…
Lots of comments are "you should compare against X and Y" - even better, just get the results on a standard benchmark, so you can compare against all, https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Still nothing beats OpenAI's VTT. Anthropic's sucks and Apple's isn't even usable. Edit: Getting downvoted by Apple fanboys for telling the truth is a badge of honor.
Whisper is the wrong model to benchmark against, or rather, there are better models that are state of the art now like Nemotron and Parakeet both by Nvidia, as well as Mistral's Voxtral and Cohere Transcribe. However, what's funny is, RIP to a lot of the paid apps that simply wrap Whisper, I'm sure Apple will make a native GUI such as a recorder app for macOS that obviates the need for these wrappers, which everyone…
Whisper is the wrong model to benchmark against, or rather, there are better models that are state of the art now like Nemotron and Parakeet both by Nvidia, as well as Mistral's Voxtral and Cohere Transcribe. However, what's funny is, RIP to a lot of the paid apps that simply wrap Whisper, I'm sure Apple will make a native GUI such as a recorder app for macOS that obviates the need for these wrappers, which everyone…
Also, this test is English-only, while a strong point of other models is to understand different languages without first having to say which one (so you don't need 3 different keyboard shortcuts if you wanna dictate in 3 languages day-to-day)
Earlier quoted context omitted.
Aside from the legality of it, I think you are underestimating how complex it can be to do that. It is possible in theory but not something that will be a fun side quest like you are making it seem.
With a IDA Pro decompiler license & MCP server, paired with Codex/Claude Code... it would be a fun side quest.
Whisper is the wrong model to benchmark against, or rather, there are better models that are state of the art now like Nemotron and Parakeet both by Nvidia, as well as Mistral's Voxtral and Cohere Transcribe. However, what's funny is, RIP to a lot of the paid apps that simply wrap Whisper, I'm sure Apple will make a native GUI such as a recorder app for macOS that obviates the need for these wrappers, which everyone…