search

savbell / whisper-writer

💬📝 A small dictation app using OpenAI's Whisper speech recognition model.
GNU General Public License v3.0
275 stars 45 forks source link

Seem to don't work #3

Closed DreamDrum closed 8 months ago

DreamDrum commented 1 year ago

Hello, sorry to disturb, im not good in python or other, and i just wanted to use your whisper-writer in adition to whister to do somes test and to talk in real time online in other language. And after all installed, following the steps, the thing start but that didn't do anything except showing the rec thing, no error or anything, just he didn't write... Maybe you have a soluce ?

DreamDrum commented 1 year ago

"Starting WhisperWriter... Script activated. Press Ctrl+Alt+Space to start recording and transcribing. Press Ctrl+C on the terminal window to quit. Recording... Recording finished. Size: 53280 Transcribing audio file... Error: Recording... Recording finished. Size: 163680 Transcribing audio file... Error: "

The only thing i have, didn't seem to work, for testing i checked if the mic worked, he worked, if the mic was the mic in "default" for the computer, etc

savbell commented 1 year ago

Hi, thank you for your comment! Apologies for taking a while to respond. I made a small update to how errors are logged in my most recent commit, so now more detailed information should be printed out to the console. Please update to the latest version and let me know what the detailed error is and I can help you resolve this! Also, if you could provide me what your settings are in the configuration file, that would be helpful as well. Thanks! :)

savbell commented 8 months ago

Closing stale issue.

DreamDrum commented 4 months ago

Sorry for the long time to answer, i litteraly forgot about that issue i posted a few time ago because i founded the error was mine, i litteraly forgot one step.

I tested a bit more, its working fine and you really made a good work.

Also i take benefit of this answer to ask you a question, The thing i still don't understand actually its how to modify the "delay" the recording have before closing the rec when i stop speaking, do you integrated a command for that ?

savbell commented 3 months ago

Hi @DreamDrum , I'm glad to hear that you were able to resolve your issue and that the app is working for you now!

Yes, you can modify the length of the delay between when the speaker stops talking and when the app stops recording. To do this, you need to modify the silence_duration configuration option in src/config.json. By default, it is set to 900 milliseconds, but you can increase it to make the delay longer or decrease it to make it shorter.

I hope that helps, and let me know if you run into any other issues! :)