update .gitignore file to ignore .pyc files

.gitignore

@@ -1,2 +1,3 @@
 *.pth
-assets/ 
+assets/ 
+__pycache__/

app.py

@@ -26,9 +26,9 @@ ASSET_DIR = "./assets"
 DEFUALT_SR = 16_000
 DEFUALT_HIGH_CUT = 8_000
 DEFUALT_LOW_CUT = 1_000
-DEVICE = "cpu" #"cuda" if torch.cuda.is_available() else "cpu"
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
 
-print(f"Device: {DEVICE}")
+print(f"Use Device: {DEVICE}")
 
 if not os.path.exists(ASSET_DIR):
     os.makedirs(ASSET_DIR)
@@ -167,12 +167,12 @@ Thomas Radinger [ [email protected] | [LinkedIn](https://www.linkedin.com
 
 Birds are key indicators of ecosystem health and play pivotal roles in maintaining biodiversity [1]. To monitor and protect bird species, automatic bird sound recognition systems are essential. These systems can help in identifying bird species, monitoring their populations, and understanding their behavior. However, building such systems is challenging due to the diversity of bird sounds, complex acoustic interference and limited labeled data. 
 
-To tackle these challenges, we expored the potential of deep learning models for bird sound recognition. In our work, we developed two Audio Spectrogram Transformer (AST) based models: BirdAST and BirdAST_Seq, to predict bird species from audio recordings. We evaluated the models on a dataset of 728 bird species and achieved promising results. As the field-recordings may contain various types of audio rather than only bird songs/calls, we also employed an Audio Masked AutoEncoder (AudioMAE) model to pre-classify audio clips into bird, insects, rain, environmental noise, and other types. Details of the models and evaluation results are provided in the table below.
+To tackle these challenges, we expored the potential of deep learning models for bird sound recognition. In our work, we developed two Audio Spectrogram Transformer (AST) based models: BirdAST and BirdAST_Seq, to predict bird species from audio recordings. We evaluated the models on a dataset of 728 bird species and achieved promising results.  Details of the models and evaluation results are provided in the table below. As the field-recordings may contain various types of audio rather than only bird songs/calls, we also employed an Audio Masked AutoEncoder (AudioMAE) model to pre-classify audio clips into bird, insects, rain, environmental noise, and other types [2].
 
 Our contributions have shown the potential of deep learning models for bird sound recognition. We hope that our work can contribute to the development of automatic bird sound recognition systems and help in monitoring and protecting bird species.
 
-
 <div align="center">
+<b>Model Details</b>
 
 | Model name       | Architecture                   | ROC-AUC Score |
 | ---------------  |:------------------------------:|:-------------:|
@@ -187,11 +187,11 @@ Our contributions have shown the potential of deep learning models for bird soun
 2. Upload an audio clip and specify the start and end time for prediction. 
 3. Click on the "Predict" button to get the predictions.
 4. In the output, you will get the audio type classification (e.g., bird, insects, rain, etc.) in the panel "Class Prediction" and the predicted bird species in the panel "Species Prediction". 
-- The audio types are predicted as multi-lable classification based on the AudioMAE model [2]. The predicted classes indicate the possible presence of different types of audio in the recording.
-- The bird species are predicted as a multi-class classification using the selected model. The predicted classes indicate the most possible bird species present in the recording. 
+    * The audio types are predicted as multi-lable classification based on the AudioMAE model. The predicted classes indicate the possible presence of different types of audio in the recording.
+    * The bird species are predicted as a multi-class classification using the selected model. The predicted classes indicate the most possible bird species present in the recording. 
 5. The waveform and spectrogram of the audio clip are displayed in the respective panels.
 
-Notes:
+**Notes:**
 - For an unknown bird species, the model may predict the most similar bird species based on the training data.
 - If an audio clip contains non-bird sounds (predicted by the AudioMAE), the bird species prediction may not be accurate.
 
@@ -307,6 +307,10 @@ def handle_model_selection(model_name, download_status):
     # Inform user that download is starting
     # gr.Info(f"Downloading model weights for {model_name}...")
     print(f"Downloading model weights for {model_name}...")
+    
+    if model_name is None:
+        model_name = "BirdAST"
+        
     assets = ASSET_DICT[model_name]
     model_weights_url = assets["model_weights"]
     download_flag = True
@@ -324,7 +328,7 @@ def handle_model_selection(model_name, download_status):
                 break
             
         if download_flag:
-            download_status =  f"Model <{model_name}> is ready for prediction!"
+            download_status =  f"Model <{model_name}> is ready! 🎉🎉🎉\nUsing Device: {DEVICE.upper()}"
         else:
             download_status = f"An error occurred while downloading model weights."
             
@@ -363,12 +367,14 @@ with gr.Blocks(theme = seafoam, css = css, js = js) as demo:
         waveform_output = gr.Plot(label="Waveform")
         spectrogram_output = gr.Plot(label="Spectrogram")
     
-    # gr.Examples(
-    #     examples=[
-    #         ["1094_Pionus_fuscus_2.wav", 0, 10],
-    #     ],
-    #     inputs=[audio_input, start_time_input, end_time_input]
-    # )
+    gr.Examples(
+        examples=[
+            ["XC226833-Chestnut-belted_20Chat-Tyrant_20A_2010989.mp3", 0, 10],
+            ["XC812290-Many-striped-Canastero_Teaben_Pe_1jul2022_FSchmitt_1.mp3", 0, 10],
+            ["XC763511-Synallaxis-maronica_Bagua-grande_MixPre-1746.mp3", 0, 10]
+        ],
+        inputs=[audio_input, start_time_input, end_time_input]
+    )
     
     gr.Button("Predict").click(predict, [audio_input, start_time_input, end_time_input, model_dropdown], [raw_class_output, species_output, waveform_output, spectrogram_output])