app2

app2.py

@@ -3,7 +3,6 @@ import gradio as gr
 import os
 import warnings
 warnings.filterwarnings("ignore")
-import IPython.display as ipd
 
 # Function to get the list of audio files in the 'rec/' directory
 def get_audio_files_list(directory="rec"):
@@ -32,7 +31,6 @@ emotion_dict = {
 
 def predict_emotion(selected_audio):
     file_path = os.path.join("rec", selected_audio)
-    ipd.display(ipd.Audio(file_path))
     out_prob, score, index, text_lab = learner.classify_file(file_path)
     return emotion_dict[text_lab[0]]
 
@@ -41,6 +39,7 @@ audio_files_list = get_audio_files_list()
 
 # Loading Gradio interface
 inputs = gr.Dropdown(label="Select Audio", choices=audio_files_list)
+audio_ui=gr.Audio()
 outputs = "text"
 title = "ML Speech Emotion Detection"
 description = "Speechbrain powered wav2vec 2.0 pretrained model on IEMOCAP dataset using Gradio."

app3.py

@@ -0,0 +1,55 @@
+import gradio as gr
+from speechbrain.pretrained.interfaces import foreign_class
+import os
+
+# Function to get the list of audio files in the 'rec/' directory
+def get_audio_files_list(directory="rec"):
+    try:
+        return [f for f in os.listdir(directory) if os.path.isfile(os.path.join(directory, f))]
+    except FileNotFoundError:
+        print("The 'rec' directory does not exist. Please make sure it is the correct path.")
+        return []
+
+# Loading the speechbrain emotion detection model
+learner = foreign_class(
+    source="speechbrain/emotion-recognition-wav2vec2-IEMOCAP",
+    pymodule_file="custom_interface.py",
+    classname="CustomEncoderWav2vec2Classifier"
+)
+
+# Building prediction function for Gradio
+emotion_dict = {
+    'sad': 'Sad',
+    'hap': 'Happy',
+    'ang': 'Anger',
+    'fea': 'Fear',
+    'sur': 'Surprised',
+    '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)
+    out_prob, score, index, text_lab = learner.classify_file(file_path)
+    emotion = emotion_dict[text_lab[0]]
+    return audio_data, emotion
+
+# 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()