Merge branch 'main' into segments-collection-mode

Author: max-mauermann

.github/workflows/ci.yml

@@ -22,6 +22,8 @@ jobs:
         python-version: ["3.11"]
     steps:
       - uses: actions/checkout@v4
+        with:
+          submodules: true
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "tests/data"]
+	path = tests/data
+	url = https://github.com/birdnet-team/birdnet-test-data.git

CONTRIBUTING.md

@@ -0,0 +1,30 @@
+### Testdata (optional)
+
+This project uses a submodule for its testdata.
+
+If you want to run the tests locally you need to initialize the submodule:
+
+```bash
+git submodule update --init --recursive
+```
+
+Or checkout the submodule during cloning:
+
+```bash
+git clone --recurse-submodules https://github.com/birdnet-team/BirdNET-Analyzer.git
+```
+
+If the testdata has changed and you want to update the repo to use the new current testdata follow these steps:
+
+```bash
+cd tests/data
+git pull origin main
+cd ..
+git add data
+git commit -m "Update testdata"
+git push
+```
+
+This will set up the repo to use the current ref of the submodule.
+
+**Note**: If you wan to add data you do so by either checking out the submodule as a regular repo and just add-commit-push from there or use the subdirectory containing the submodule like a regular git repository (don't forget to manually update the ref in the main repo)

birdnet_analyzer/analyze/core.py

@@ -219,10 +219,10 @@ def _set_params(
         if custom_classifier.endswith(".tflite"):
             cfg.LABELS_FILE = custom_classifier.replace(".tflite", "_Labels.txt")  # same for labels file
 
-            if not os.path.isfile(cfg.LABELS_FILE):
+            if not os.path.isfile(cfg.LABELS_FILE): # if the label file is not found, an old birdnet model might be used
                 cfg.LABELS_FILE = custom_classifier.replace("Model_FP32.tflite", "Labels.txt")
 
-            if not custom_classifier.endswith("Model_FP32.tflite") or not os.path.isfile(cfg.LABELS_FILE):
+            if not os.path.isfile(cfg.LABELS_FILE): # if the label file is still not found, dont use labels
                 cfg.LABELS_FILE = None
                 cfg.LABELS = None
             else:

birdnet_analyzer/analyze/utils.py

@@ -208,8 +208,8 @@ def generate_csv(timestamps: list[str], result: dict[str, list], afile_path: str
     columns_map = {}
 
     if cfg.ADDITIONAL_COLUMNS:
-        for col in cfg.ADDITIONAL_COLUMNS:
-            if col in POSSIBLE_ADDITIONAL_COLUMNS_MAP:
+        for col in POSSIBLE_ADDITIONAL_COLUMNS_MAP:
+            if col in cfg.ADDITIONAL_COLUMNS:
                 columns_map[col] = POSSIBLE_ADDITIONAL_COLUMNS_MAP[col]()
 
         if columns_map:

birdnet_analyzer/embeddings/utils.py

@@ -50,8 +50,7 @@ def analyze_file(item, db: sqlite_usearch_impl.SQLiteUsearchDB):
 
                 # Insert into database
                 db.insert_embedding(embeddings, embeddings_source)
-                db.commit()
-
+        db.commit()
     except Exception as ex:
         # Write error log
         print(f"Error: Cannot analyze audio file {fpath}.", flush=True)

birdnet_analyzer/gui/embeddings.py

@@ -212,13 +212,15 @@ def select_directory_to_state_and_tb(state_key):
                     minimum=1,
                     interactive=True,
                 )
+
                 threads_number = gr.Number(
                     precision=1,
                     label=loc.localize("embedding-settings-threads-number-label"),
                     value=4,
                     info=loc.localize("embedding-settings-threads-number-info"),
                     minimum=1,
                     interactive=True,
+                    visible=False, # Threads are currently not used as its not compatible with
                 )
 
             with gr.Row():

birdnet_analyzer/gui/multi_file.py

@@ -22,6 +22,7 @@
     "Model file": "model",
 }
 
+
 @gu.gui_runtime_error_handler
 def run_batch_analysis(
     output_path,
@@ -64,7 +65,7 @@ def run_batch_analysis(
     if fmin is None or fmax is None or fmin < cfg.SIG_FMIN or fmax > cfg.SIG_FMAX or fmin > fmax:
         raise gr.Error(f"{loc.localize('validation-no-valid-frequency')} [{cfg.SIG_FMIN}, {cfg.SIG_FMAX}]")
 
-    return run_analysis(
+    results = run_analysis(
         None,
         output_path,
         use_top_n,
@@ -96,6 +97,8 @@ def run_batch_analysis(
         progress,
     )
 
+    return [path for path, successful in results if not successful]
+
 
 def build_multi_analysis_tab():
     with gr.Tab(loc.localize("multi-tab-title")):
@@ -219,7 +222,6 @@ def select_directory_wrapper():  # Nishant - Function modified for For Folder se
         result_grid = gr.Matrix(
             headers=[
                 loc.localize("multi-tab-result-dataframe-column-file-header"),
-                loc.localize("multi-tab-result-dataframe-column-execution-header"),
             ],
         )
 

birdnet_analyzer/gui/utils.py

@@ -4,6 +4,7 @@
 import multiprocessing
 import os
 import sys
+import warnings
 from collections.abc import Callable
 from contextlib import suppress
 from pathlib import Path
@@ -16,6 +17,7 @@
 from birdnet_analyzer import utils
 from birdnet_analyzer.gui import settings
 
+warnings.filterwarnings("ignore")
 loc.load_local_state()
 
 SCRIPT_DIR = os.path.abspath(os.path.dirname(__file__))
@@ -605,10 +607,10 @@ def on_custom_classifier_selection_click():
                 if not os.path.isfile(labels):
                     labels = file.replace("Model_FP32.tflite", "Labels.txt")
 
-                    if not file.endswith("Model_FP32.tflite") or not os.path.isfile(labels):
-                        gr.Warning(loc.localize("species-list-custom-classifier-no-labelfile-warning"))
+                if not os.path.isfile(labels):
+                    gr.Warning(loc.localize("species-list-custom-classifier-no-labelfile-warning"))
 
-                        return file, gr.File(value=[file], visible=True)
+                    return file, gr.File(value=[file], visible=True)
 
                 return file, gr.File(value=[file, labels], visible=True)
 

birdnet_analyzer/lang/de.json

@@ -152,8 +152,7 @@
     "multi-tab-output-selection-button-label": "Ausgabeverzeichnis auswählen",
     "multi-tab-output-textbox-label": "Ausgabeverzeichnis",
     "multi-tab-output-textbox-placeholder": "Wenn nicht ausgewählt, wird das Eingabeverzeichnis verwendet.",
-    "multi-tab-result-dataframe-column-execution-header": "Ausführung",
-    "multi-tab-result-dataframe-column-file-header": "Datei",
+    "multi-tab-result-dataframe-column-file-header": "Ungültige Audiodateien",
     "multi-tab-samples-dataframe-column-duration-header": "Länge",
     "multi-tab-samples-dataframe-column-subpath-header": "Unterpfad",
     "multi-tab-samples-dataframe-no-files-found": "Keine Dateien gefunden",