-
Notifications
You must be signed in to change notification settings - Fork 198
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
Use live audio #5
Comments
I'm also interested in this topic. |
This would be fine, also interested. |
I was able to make Live Audio work as follows. Perhaps it is a naive approach but it seems robust.
Analysing a 3s clip on a Raspberry Pi 4 only takes about 0.5s, so this scheme should never fall behind real-time (ignoring the 3s delay for sampling the audio) |
Hello Stefan,
Can you support us with the scripts via GitHub?
…--
Christoph Lauer
web: WebPage <https://christoph-lauer.github.io/>
mail: ***@***.*** ***@***.***>
tel.: 0159/01007198 <tel:0159/01007198>
Am 30.08.2021 um 01:35 schrieb Michael Ruppe ***@***.***>:
I was able to make Live Audio work as follows
Create a script that records audio in 3 second clips and stashes them in a working directory. Only record up to a maximum number of clips eg. 2 files.
Modify the analysis script to scan for files in the working directory - process the oldest file and then delete it.
Run these scripts as separate processes. The recording script will fill the directory and the analyses script will empty it.
Analysing a 3s clip on a Raspberry Pi 4 only takes about 0.5s, so this scheme should never fall behind real-time (ignoring the 3s delay for sampling the audio)
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub <#5 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ASVZ3MBVX2JZ356VJYLQTGTT7K72VANCNFSM46CXZKHQ>.
|
Hi @CoreProduction, hi @kahst |
I am also highly interested in a walk-trough (especially for the Tensorflow installation) for the Raspberry Pi 4.
…--
Christoph Lauer
web: WebPage <https://christoph-lauer.github.io/>
mail: ***@***.*** ***@***.***>
tel.: 0159/01007198 <tel:0159/01007198>
Am 08.09.2021 um 15:23 schrieb nilspupils ***@***.***>:
Hi CoreProduction, hi Stefan Kahl
as i am also in the process of setting up a live stream analysis (and struggeling a bit) would you be so kind and share your scripts for live audio with us?
Also if anyone could give a walkthrough of setting up BirdNET on a Pi 4 this would be super nice!
Thanks and greetings!
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub <#5 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ASVZ3MHE4ZCHRAHBL2GCKODUA5PV7ANCNFSM46CXZKHQ>.
|
To keep this issue reserved to the live audio input i am going to open a new issue relating to BirdNET and Tensorflow installation on the Raspberry Pi 4. Please comment there! |
I also struggle with the Tensorflow installation ob Raspberry Pi 4...
|
@Christoph-Lauer: Please use the new issue i opened for the topic on installation. Instead of compiling yourself you could have used a precompiled bin from: |
I'm looking for docs to use live audio stream as input for a BirdNET-Lite based application like the live stream demo:
https://birdnet.cornell.edu/live/
Is it possible to do this with the current setup as well?
The text was updated successfully, but these errors were encountered: