Update app.py

app.py

@@ -1,6 +1,8 @@
-import gradio as gr
 from speechbrain.pretrained.interfaces import foreign_class
+import gradio as gr
 import os
+import warnings
+warnings.filterwarnings("ignore")
 
 # Function to get the list of audio files in the 'rec/' directory
 def get_audio_files_list(directory="rec"):
@@ -13,13 +15,13 @@ def get_audio_files_list(directory="rec"):
 # Loading the speechbrain emotion detection model
 learner = foreign_class(
     source="speechbrain/emotion-recognition-wav2vec2-IEMOCAP",
-    pymodule_file="custom_interface.py",
+    pymodule_file="custom_interface.py", 
     classname="CustomEncoderWav2vec2Classifier"
 )
 
 # Building prediction function for Gradio
 emotion_dict = {
-    'sad': 'Sad',
+    'sad': 'Sad', 
     'hap': 'Happy',
     'ang': 'Anger',
     'fea': 'Fear',
@@ -27,29 +29,21 @@ emotion_dict = {
     'neu': 'Neutral'
 }
 
-def selected_audio(audio_file):
-    if audio_file is None:
-        return None, "Please select an audio file."
-    file_path = os.path.join("rec", audio_file)
-    audio_data = gr.Audio(file=file_path)
+def predict_emotion(selected_audio):
+    file_path = os.path.join("rec", selected_audio)
     out_prob, score, index, text_lab = learner.classify_file(file_path)
     emotion = emotion_dict[text_lab[0]]
-    return audio_data, emotion
+    return emotion, file_path  # Return both emotion and file path
 
 # Get the list of audio files for the dropdown
 audio_files_list = get_audio_files_list()
 
-# Define Gradio blocks
-with gr.Blocks() as blocks:
-    gr.Markdown("<h1 style='text-align: center; margin-bottom: 1rem'>" +
-                "Audio Emotion Detection" +
-                "</h1>")
-    with gr.Column():
-        input_audio_dropdown = gr.Dropdown(label="Select Audio", choices=audio_files_list)
-        audio_ui = gr.Audio()
-        output_text = gr.Textbox(label="Detected Emotion!")
-        detect_btn = gr.Button("Detect Emotion")
-        detect_btn.click(selected_audio, inputs=input_audio_dropdown, outputs=[audio_ui, output_text])
-
-# Launch the Gradio blocks interface
-blocks.launch()
+# Loading Gradio interface
+inputs = gr.Dropdown(label="Select Audio", choices=audio_files_list)
+outputs = [gr.outputs.Textbox(label="Predicted Emotion"), gr.outputs.Audio(label="Play Audio")]
+
+title = "ML Speech Emotion Detection3"
+description = "Speechbrain powered wav2vec 2.0 pretrained model on IEMOCAP dataset using Gradio."
+
+interface = gr.Interface(fn=predict_emotion, inputs=inputs, outputs=outputs, title=title, description=description)
+interface.launch()