Open jeroenboumans opened 3 years ago
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 https://github.com/kahst/BirdNET-Lite/issues/5#issuecomment-907898741, or unsubscribe https://github.com/notifications/unsubscribe-auth/ASVZ3MBVX2JZ356VJYLQTGTT7K72VANCNFSM46CXZKHQ.
Hi @CoreProduction, hi @kahst 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!
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 https://github.com/kahst/BirdNET-Lite/issues/5#issuecomment-915235625, 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: https://github.com/PINTO0309/TensorflowLite-bin
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?