Earlier quoted context omitted.
Slower
Yours isn't OSS, meaning I have no idea what I'm running
Show HN: Scriber Pro – Offline AI transcription for macOS
31–40 of 120 posts
Re: Show HN: Scriber Pro – Offline AI transcription for macOS
#32Cool project, I am using ChatGPT for recording/summarising meetings but the limit there is 2 hours
Re: Show HN: Scriber Pro – Offline AI transcription for macOS
#33Re: Show HN: Scriber Pro – Offline AI transcription for macOS
#34[stub for offtopicness]
https://scriberpro.cc/about/ Are you trolling people with this page's design? Unreadable colors AND a wobble effect? :D
Re: Show HN: Scriber Pro – Offline AI transcription for macOS
#35Earlier quoted context omitted.
Yours isn't OSS, meaning I have no idea what I'm running
OSS would be incredibly slow, also seems like overkill for this use case
Re: Show HN: Scriber Pro – Offline AI transcription for macOS
#36Re: Show HN: Scriber Pro – Offline AI transcription for macOS
#37Re: Show HN: Scriber Pro – Offline AI transcription for macOS
#38Earlier quoted context omitted.
MacWhisper crashes at about an hour of context. This uses, smart, invisible regex in the text generation pipe. Makes this fast. + bonus, there is no context limit
"Smart, invisible regex" sounds like a lot of bs... could you give a more technical explanation? Also the Whisper model doesn't really have a context window, it already segments the audio with a certain amount of overlap between the chunks, I really have a hard time understanding what you are trying to say here.
Re: Show HN: Scriber Pro – Offline AI transcription for macOS
#39[stub for offtopicness]
Re: Show HN: Scriber Pro – Offline AI transcription for macOS
#40Earlier quoted context omitted.
"Smart, invisible regex" sounds like a lot of bs... could you give a more technical explanation? Also the Whisper model doesn't really have a context window, it already segments the audio with a certain amount of overlap between the chunks, I really have a hard time understanding what you are trying to say here.
Whisper will fail > 99%* (edit, most of the time) of the time at lengths over 90 minutes and fairly high over one hour.