-
-
Notifications
You must be signed in to change notification settings - Fork 15
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Real time Transcription #49
Comments
This is an interesting feature that I'd have to thoroughly explore to see how it could be implemented in Audiotext. Thanks for the suggestion! |
Great! Do you have any implementation plan or when you think it can become available? |
I can't answer either because, as I said, I need to thoroughly see how to implement it. Also, I would like to build the MacOS and Linux executables before tackling this issue, so I don't know how long it will take to implement this feature. |
I completely understand. Just keep the issue posted
…On Fri, Aug 2, 2024 at 3:44 PM HenestrosaDev ***@***.***> wrote:
I can't answer either because, as I said, I need to thoroughly see how to
implement it. Also, I would like to build the MacOS and Linux executables
before tackling this issue, so I don't know how long it will take to
implement this feature.
—
Reply to this email directly, view it on GitHub
<#49 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AMSQ2BHO7J7OQRKIJLJ65WTZPOLODAVCNFSM6AAAAABLR6S6OSVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDENRVGU3DONJUGY>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
|
This would be a GREAT feature, I support this idea + Whisper X |
Do you have any idea on how to implement it? |
This is just a heads up that I'm currently working on this feature. It will be available in version 2.3.1. |
Awesome and Thank you. Let us know as this progress... |
One way to implement it is using CUDA for Nvidia Graphics Cards for faster results and better time responses and/or CPU Mode for those that don't have a NVIDIA GPU for transcribing in real time with the models (large, medium, etc...). Also, you could implement the ability to use the microphone for real time transcriptions that are in live, and/or the option to select a device and make the program listen the audio of the pc (for example with the help of VoiceMeeter to capture your system audio as virtual input) for those who want to transcribe in real time an audio, call or video that is playing on your pc (which is different to select a file and wait x minutes to wait until it is transcribe) That's one way to do it |
How is this progressing? |
Make the recording option of the transcription real-time
This will make it easier to use the application in a live transcription scenario.
Instead of the microphone recording alone, as it records in set time, it will keep transcribing and appending it.
I'm willing to implement this as a means of contributing if the guidance is provided.
Thanks for the awesome software!
The text was updated successfully, but these errors were encountered: