Now we just need text to speech so we can truly interact with our computers hands free.
Show HN: Whispering – Open-source, local-first dictation you can trust
11–20 of 159 posts
Re: Show HN: Whispering – Open-source, local-first dictation you can trust
#12Does Whispering support semantic correction? I was unable to find confirmation while doing a quick search.
Hmm, we support prompts at both 1. the model level (the Whisper supports a "prompt" parameter that sometimes works) and 2. transformations level (inject the transcribed text into a prompt and get the output from an LLM model of your choice). Unsure how else semantic correction can be implemented, but always open expand the feature set greatly over the next few weeks!
They might not now how whisper works. I suspect that the answer to their question is 'yes' and the reason they can't find a straightforward answer through your project is that the answer is so obvious to you that it's hardly worth documenting.
Whisper for transcription tries to transform audio data into LLM output. The transcripts generally have proper casing, punctuation and can usually stick to a specific domain based on the surrounding context.
Re: Show HN: Whispering – Open-source, local-first dictation you can trust
#13Does this support using the Parakeet model locally? I'm a MacWhisper user and I find that Parakeet is way better and faster than Whisper for on-device transcription. I've been using push-to-transcribe with MacWhisper through Parakeet for a while now and it's quite magical.
Re: Show HN: Whispering – Open-source, local-first dictation you can trust
#14Windows Defender says it is infected.
Re: Show HN: Whispering – Open-source, local-first dictation you can trust
#15Windows Defender says it is infected.
This needs to be higher, the installer on the README has a trojan.
Re: Show HN: Whispering – Open-source, local-first dictation you can trust
#16am I not getting it correctly; it says local is possible but can't find any information about how to run it without any api key?
I get the whispers models, and do what? how to run in a device without internet, no documentation about it...
Re: Show HN: Whispering – Open-source, local-first dictation you can trust
#17Windows Defender says it is infected.
I'm no expert, but since it acts as a keyboard wedge it's likely to be unpopular with security software.
Re: Show HN: Whispering – Open-source, local-first dictation you can trust
#18am I not getting it correctly; it says local is possible but can't find any information about how to run it without any api key? I get the whispers models, and do what? how to run in a device without internet, no documentation about it...
The docs are pretty clear that you need to use speaches if you want entirely local operation.
Re: Show HN: Whispering – Open-source, local-first dictation you can trust
#19am I not getting it correctly; it says local is possible but can't find any information about how to run it without any api key? I get the whispers models, and do what? how to run in a device without internet, no documentation about it...
Commented this earlier, but I'm in the middle of a release that adds Whisper C++ support!
https://github.com/epicenter-so/epicenter/pull/655
After this pushes, we'll have far more extensive local transcription support. Just fixing a few more small things :)