avm/hassio-addons
1
0
Fork 0
mirror of https://github.com/alexbelgium/hassio-addons.git synced 2026-01-09 09:21:03 +01:00
Code Issues Packages Projects Releases Wiki Activity

Lint

Browse Source
This commit is contained in:
alexbelgium
2025-05-28 09:09:13 +02:00
parent 9839bfb32b
commit eace8e8cd8
1 changed files with 11 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
birdnet-pi/DOCS.md
View File

@@ -24,19 +24,19 @@ Here are some example tests I did (the whole threads are really interesting also
I've tested lots of settings by running 2 versions of my HA birdnet-pi addon in parallel using the same RTSP feed and comparing the impact of parameters. My conclusions aren't universal, as it seems to be highly dependent on the region and type of mic used. For example, the old model seems to be better in Australia, while the new one is better in Europe.
- **Model**
- **Version:** 6k_v2.4 _(performs better in Europe at least, the 6k performs better in Australia)_
- **Species range model:** v1 _(uncheck v2.4; seems more robust in Europe)_
- **Species occurrence threshold:** 0.001 _(was 0.00015 using v2.4; use the Species List Tester to check the correct value for you)_
- **Version:** 6k_v2.4 _(performs better in Europe at least, the 6k performs better in Australia)_
- **Species range model:** v1 _(uncheck v2.4; seems more robust in Europe)_
- **Species occurrence threshold:** 0.001 _(was 0.00015 using v2.4; use the Species List Tester to check the correct value for you)_
- **Audio settings**
- **Default**
- **Channel:** 1 _(doesn't really matter as analysis is made on mono signal; 1 allows decreased saved audio size but seems to give slightly messed up spectrograms in my experience)_
- **Recording Length:** 18 _(that's because I use an overlap of 0.5; so it analyzes 0-3s, 2.5-5.5s, 5-8s, 7.5-10.5, 10-13, 12.5-15.5, 15-18)_
- **Extraction Length:** 9s _(could be 6, but I like to hear my birds :-))_
- **Audio format:** mp3 _(why bother with something else)_
- **Default**
- **Channel:** 1 _(doesn't really matter as analysis is made on mono signal; 1 allows decreased saved audio size but seems to give slightly messed up spectrograms in my experience)_
- **Recording Length:** 18 _(that's because I use an overlap of 0.5; so it analyzes 0-3s, 2.5-5.5s, 5-8s, 7.5-10.5, 10-13, 12.5-15.5, 15-18)_
- **Extraction Length:** 9s _(could be 6, but I like to hear my birds :-))_
- **Audio format:** mp3 _(why bother with something else)_
- **Birdnet-lite settings**
- **Overlap:** 0.5s
- **Minimum confidence:** 0.7
- **Sigmoid sensitivity:** 1.25 _(I've tried 1.00 but it gave much more false positives; decreasing this value increases sensitivity)_
- **Overlap:** 0.5s
- **Minimum confidence:** 0.7
- **Sigmoid sensitivity:** 1.25 _(I've tried 1.00 but it gave much more false positives; decreasing this value increases sensitivity)_
# Set RTSP server