Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Change from birdnetlib to birdnet #392

Merged
merged 2 commits into from
Jul 24, 2024
Merged

Change from birdnetlib to birdnet #392

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
df82eaa
Change from birdnetlib to birdnet
stefantaubert Jul 24, 2024
a0208d4
Change heading
stefantaubert Jul 24, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
41 changes: 20 additions & 21 deletions README.adoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -237,41 +237,40 @@ For more information on how to use this feature, please visit the https://ravens

https://tuc.cloud/index.php/s/2TX59Qda2X92Ppr/download/BirdNET_GLOBAL_6K_V2.4_Model_Raven.zip[Download the newest model version here], extract the zip-file and move the extracted folder to the Raven models folder. On Windows, the models folder is `C:\Users\<Your user name>\Raven Pro 1.6\Models`. Start Raven Pro and select *BirdNET_GLOBAL_6K_V2.4_Model_Raven* as learning detector.

=== Setup (birdnetlib)
=== Setup (Python package)

The easiest way to setup BirdNET on your machine is to install https://pypi.org/project/birdnetlib/[birdnetlib] through pip with:
The easiest way to setup BirdNET on your machine is to install https://pypi.org/project/birdnet/[birdnet] through pip with:

[source,sh]
----
pip3 install birdnetlib
pip3 install birdnet
----

Make sure to install Tensorflow Lite, librosa and ffmpeg like mentioned below.
You can run BirdNET with:

[source,python]
----
from birdnetlib import Recording
from birdnetlib.analyzer import Analyzer
from datetime import datetime
from pathlib import Path
from birdnet.models import ModelV2M4

# Load and initialize the BirdNET-Analyzer models.
analyzer = Analyzer()
# create model instance for v2.4
model = ModelV2M4()

recording = Recording(
analyzer,
"sample.mp3",
lat=35.4244,
lon=-120.7463,
date=datetime(year=2022, month=5, day=10), # use date or week_48
min_conf=0.25,
# predict species within the whole audio file
species_in_area = model.predict_species_at_location_and_time(42.5, -76.45, week=4)
predictions = model.predict_species_within_audio_file(
Path("soundscape.wav"),
filter_species=set(species_in_area.keys())
)
recording.analyze()
print(recording.detections)

# get most probable prediction at time interval 0s-3s
prediction, confidence = list(predictions[(0.0, 3.0)].items())[0]
print(f"predicted '{prediction}' with a confidence of {confidence:.6f}")
# predicted 'Poecile atricapillus_Black-capped Chickadee' with a confidence of 0.814056
----

For more examples and documentation, make sure to visit https://pypi.org/project/birdnetlib/[pypi.org/project/birdnetlib/].
For any feature request or questions regarding *birdnetlib*, please contact link:mailto:joe.weiss@gmail.com[Joe Weiss] or add an issue or PR at https://github.com/joeweiss/birdnetlib[github.com/joeweiss/birdnetlib].
For more examples and documentation, make sure to visit https://pypi.org/project/birdnet/[pypi.org/project/birdnet/].
For any feature request or questions regarding *birdnet*, please add an issue or PR at https://github.com/birdnet-team/birdnet[github.com/birdnet-team/birdnet].

=== Setup (Ubuntu)

Expand Down Expand Up @@ -436,7 +435,7 @@ Subsequent runs will be faster.
python analyze.py
----

NOTE: Now, you can install and use <<setup-birdnetlib,birdnetlib>>.
NOTE: Now, you can install and use <<_setup_python_package,birdnet>>.

== Usage
=== Usage (CLI)
Expand Down