### Example detection output

Source: https://joeweiss.github.io/birdnetlib/api

Sample output structure when return_all_detections is enabled.

```json
[{'common_name': 'Spotted Crake',
  'confidence': 0.7721,
  'end_time': 12.0,
  'scientific_name': 'Porzana porzana',
  'start_time': 9.0,
  'is_predicted_for_location_and_date': False,
  'label': 'Haemorhous mexicanus_House Finch'},
 {'common_name': 'House Finch',
  'confidence': 0.4496,
  'end_time': 15.0,
  'scientific_name': 'Haemorhous mexicanus',
  'start_time': 12.0,
  'is_predicted_for_location_and_date': True,
  'label': 'Haemorhous mexicanus_House Finch'}]
```

--------------------------------

### Install birdnetlib

Source: https://joeweiss.github.io/birdnetlib/getting-started

Install the package using pip. Ensure Python 3.9+ and dependencies like Tensorflow Lite, librosa, and ffmpeg are installed first.

```bash
pip install birdnetlib
```

--------------------------------

### Install birdnetlib

Source: https://joeweiss.github.io/birdnetlib

Install the birdnetlib package using pip. Ensure Python 3.9+ and prior installation of Tensorflow Lite, librosa, and ffmpeg.

```bash
pip install birdnetlib

```

--------------------------------

### Detection Output Format

Source: https://joeweiss.github.io/birdnetlib/getting-started

Example structure of the list returned by recording.detections containing species information and confidence scores.

```json
[{'common_name': 'House Finch',
  'confidence': 0.5744,
  'end_time': 12.0,
  'scientific_name': 'Haemorhous mexicanus',
  'start_time': 9.0,
  'label': 'Haemorhous mexicanus_House Finch'},
 {'common_name': 'House Finch',
  'confidence': 0.4496,
  'end_time': 15.0,
  'scientific_name': 'Haemorhous mexicanus',
  'start_time': 12.0,
  'label': 'Haemorhous mexicanus_House Finch'}]
```

--------------------------------

### Extract feature embeddings

Source: https://joeweiss.github.io/birdnetlib/api

Use extract_embeddings to get feature vectors instead of classification results.

```python
from birdnetlib import Recording
from birdnetlib.analyzer import Analyzer

analyzer = Analyzer()
recording = Recording(
    analyzer,
    "sample.mp3",
)
recording.extract_embeddings()
print(recording.embeddings)
```

--------------------------------

### Analyze audio with LiteAnalyzer

Source: https://joeweiss.github.io/birdnetlib/api

Initializes the analyzer and processes an audio file. The model is downloaded automatically upon the first instantiation.

```python
analyzer = LiteAnalyzer()

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,
)
recording.analyze()
print(recording.detections) # Returns list of detections.
```

--------------------------------

### Analyze Audio with Analyzer

Source: https://joeweiss.github.io/birdnetlib/getting-started

Initialize the Analyzer and process a recording file to identify bird species. Requires providing latitude, longitude, and date for accurate model inference.

```python
from birdnetlib import Recording
from birdnetlib.analyzer import Analyzer
from datetime import datetime

# Load and initialize the BirdNET-Analyzer models.
analyzer = Analyzer()

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,
)
recording.analyze()
print(recording.detections)
```

--------------------------------

### Initialize LiteAnalyzer

Source: https://joeweiss.github.io/birdnetlib/api

Initialize the legacy LiteAnalyzer class.

```python
from birdnetlib import Recording
from birdnetlib.analyzer_lite import LiteAnalyzer
from datetime import datetime

# Load and initialize the BirdNET-Lite models.
```

--------------------------------

### Analyze Audio Files in a Directory with Multiprocessing

Source: https://joeweiss.github.io/birdnetlib/utility-classes

Employ DirectoryMultiProcessingAnalyzer for asynchronous analysis of audio files in a directory using multiple processes. The results are returned as a list of recordings.

```python
def on_analyze_directory_complete(recordings):
    for recording in recordings:
        pprint(recording.detections)

directory = "."
batch = DirectoryMultiProcessingAnalyzer(
    "/Birds/mp3_dir",
    patterns=["*.mp3", "*.wav"]
)

batch.on_analyze_directory_complete = on_analyze_directory_complete
batch.process()

```

--------------------------------

### Use custom classifier

Source: https://joeweiss.github.io/birdnetlib/api

Configure the Analyzer with custom model and label files.

```python
from birdnetlib import Recording
from birdnetlib.analyzer import Analyzer

# Load and initialize BirdNET-Analyzer with your own model/labels.

custom_model_path = "custom_classifiers/trogoniformes.tflite"
custom_labels_path = "custom_classifiers/trogoniformes.txt"

analyzer = Analyzer(
    classifier_labels_path=custom_labels_path, classifier_model_path=custom_model_path
)

recording = Recording(
    analyzer,
    "sample.mp3",
    min_conf=0.25,
)
recording.analyze()
print(recording.detections)
```

--------------------------------

### Watch a Directory for New Audio Files

Source: https://joeweiss.github.io/birdnetlib/utility-classes

Utilize DirectoryWatcher to monitor a directory for newly created audio files and automatically analyze them. A callback function is used to process each analyzed recording.

```python
def on_analyze_complete(recording):
    print(recording.path)
    pprint(recording.detections)

watcher = DirectoryWatcher("/Birds/mp3_dir")
watcher.on_analyze_complete = on_analyze_complete
watcher.watch()

```

--------------------------------

### Analyze a recording file

Source: https://joeweiss.github.io/birdnetlib/api

Basic usage of the Recording class to analyze an audio file from disk.

```python
from birdnetlib import Recording
from birdnetlib.analyzer import Analyzer

analyzer = Analyzer()

recording = Recording(
    analyzer,
    "sample.mp3",
    min_conf=0.25,
)
recording.analyze()
print(recording.detections)
```

--------------------------------

### Analyze Audio Files in a Directory

Source: https://joeweiss.github.io/birdnetlib/utility-classes

Use DirectoryAnalyzer to process all audio files matching specified patterns within a directory. Define a callback function to handle analysis results.

```python
def on_analyze_complete(recording):
    print(recording.path)
    pprint(recording.detections)

directory = DirectoryAnalyzer(
    "/Birds/mp3_dir",
    patterns=["*.mp3", "*.wav"]
)
directory.on_analyze_complete = on_analyze_complete
directory.process()

```

--------------------------------

### Analyze in-memory file object

Source: https://joeweiss.github.io/birdnetlib/api

Use RecordingFileObject to process audio data stored in memory.

```python
with io.BytesIO(r.content) as fileObj:
    recording = RecordingFileObject(
        analyzer,
        fileObj,
        lat=35.6,
        lon=-77.3,
        date=datetime(year=2023, month=6, day=27),  # use date or week_48
        min_conf=0.25,
    )
    recording.analyze()
    pprint(recording.detections)
```

--------------------------------

### Analyze Audio with BirdNET-Analyzer

Source: https://joeweiss.github.io/birdnetlib

Use the Analyzer class to load BirdNET-Analyzer models and process an audio file. Specify latitude, longitude, and date for accurate analysis. The 'recording.detections' attribute will contain a list of detected species with confidence scores and time ranges.

```python
from birdnetlib import Recording
from birdnetlib.analyzer import Analyzer
from datetime import datetime

# Load and initialize the BirdNET-Analyzer models.
analyzer = Analyzer()

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,
)
recording.analyze()
print(recording.detections)

```

```python
[{'common_name': 'House Finch',
  'confidence': 0.5744,
  'end_time': 12.0,
  'scientific_name': 'Haemorhous mexicanus',
  'start_time': 9.0,
  'label': 'Haemorhous mexicanus_House Finch'},
 {'common_name': 'House Finch',
  'confidence': 0.4496,
  'end_time': 15.0,
  'scientific_name': 'Haemorhous mexicanus',
  'start_time': 12.0,
  'label': 'Haemorhous mexicanus_House Finch'}]

```

--------------------------------

### Initialize specific analyzer version

Source: https://joeweiss.github.io/birdnetlib/api

Specify the model version when initializing the Analyzer class.

```python
# Load and initialize the BirdNET-Analyzer 2.3 model.
analyzer = Analyzer(version="2.3")
```

--------------------------------

### Filter detections by location and date

Source: https://joeweiss.github.io/birdnetlib/api

Use lat, lon, and date arguments to filter detections based on species presence.

```python
from birdnetlib import Recording
from birdnetlib.analyzer import Analyzer

analyzer = Analyzer()

recording = Recording(
    analyzer,
    "sample.mp3",
    min_conf=0.25,
    lat=35.6,
    lon=-77.3,
    date=datetime(year=2023, month=6, day=27),
)
recording.analyze()
print(recording.detections)
```

--------------------------------

### Annotate detections with occurrence prediction

Source: https://joeweiss.github.io/birdnetlib/api

Set return_all_detections to True to include an occurrence prediction flag for each detection.

```python
from birdnetlib import Recording
from birdnetlib.analyzer import Analyzer

analyzer = Analyzer()

recording = Recording(
    analyzer,
    "sample.mp3",
    min_conf=0.25,
    lat=35.6,
    lon=-77.3,
    date=datetime(year=2023, month=6, day=27),
    return_all_detections=True,
)
recording.analyze()
print(recording.detections)
```

--------------------------------

### Predict Species List by Location and Date

Source: https://joeweiss.github.io/birdnetlib/utility-classes

Use SpeciesList to predict a list of bird species based on geographical coordinates and a specific date. The output includes scientific name, common name, and prediction threshold.

```python
species = SpeciesList()
species_list = species.return_list(
    lon=-120.7463, lat=35.4244, date=datetime(year=2022, month=5, day=10)
)
print(species_list)
# [{'scientific_name': 'Haemorhous mexicanus', 'common_name': 'House Finch', 'threshold': 0.8916686}, ...]

```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.