Update app.py

app.py

@@ -1,17 +1,9 @@
 from speechbrain.pretrained.interfaces import foreign_class
-
-import warnings
-warnings.filterwarnings("ignore")
-
-import os
 import gradio as gr
+import os
+import warnings
 
-# Путь к каталогу с предзаписанными аудиофайлами
-prerecorded_audio_path = 'prerecordered'
-# Список файлов в каталоге prerecorded
-prerecorded_audio_files = os.listdir(prerecorded_audio_path)
-# Полные пути к файлам для Dropdown
-prerecorded_audio_files_full_path = [os.path.join(prerecorded_audio_path, file) for file in prerecorded_audio_files]
+warnings.filterwarnings("ignore")
 
 # Loading the speechbrain emotion detection model
 learner = foreign_class(
@@ -20,7 +12,7 @@ learner = foreign_class(
     classname="CustomEncoderWav2vec2Classifier"
 )
 
-# Building prediction function for gradio
+# Emotion dictionary
 emotion_dict = {
     'sad': 'Sad',
     'hap': 'Happy',
@@ -30,33 +22,48 @@ emotion_dict = {
     'neu': 'Neutral'
 }
 
-def predict_emotion(uploaded_audio=None, prerecorded_audio=None):
-    # Если выбран аудиофайл из выпадающего списка, использовать его
-    if prerecorded_audio is not None:
-        audio_file_path = prerecorded_audio
-    elif uploaded_audio is not None:
-        # Иначе, если загружен файл, использовать его
-        audio_file_path = uploaded_audio.name
-    else:
-        # Если нет файла, вернуть сообщение об ошибке
-        return "No audio file provided", 0
-
-    out_prob, score, index, text_lab = learner.classify_file(audio_file_path)
-    emotion_probability = out_prob[0][index[0]].item()
-    
-    # Возвращаем словарь с эмоцией и вероятностью
-    return {"Emotion": emotion_dict[text_lab[0]], "Probability": f"{emotion_probability:.2f}"}
-
-# Модифицированный Gradio interface
-inputs = [
-    gr.inputs.Dropdown(list(prerecorded_audio_files_full_path), label="Select Prerecorded Audio", default=None),
-    gr.inputs.Audio(label="Or Upload Audio", type="file", source="upload", optional=True),
-    gr.inputs.Audio(label="Or Record Audio", type="file", source="microphone", optional=True)
-]
-
-outputs = gr.outputs.Label(num_top_classes=2)
-
-title = "ML Speech Emotion Detection"
-description = "Detect emotions from speech using a Speechbrain powered model."
-
-gr.Interface(fn=predict_emotion, inputs=inputs, outputs=outputs, title=title, description=description).launch()
+# Function for classification of uploaded files
+def predict_emotion_upload(audio):
+    out_prob, score, index, text_lab = learner.classify_file(audio.name)
+    return emotion_dict[text_lab[0]]
+
+# Function for classification of selected files from the dropdown
+def predict_emotion_select(filename):
+    file_path = os.path.join('rec', filename)
+    out_prob, score, index, text_lab = learner.classify_file(file_path)
+    return emotion_dict[text_lab[0]]
+
+# Function to create an audio player component
+def create_audio_player(filename):
+    file_path = os.path.join('rec', filename)
+    return file_path
+
+# Retrieve a list of audio file names from the 'rec' directory
+audio_files = os.listdir('rec')
+audio_files_dropdown = gr.inputs.Dropdown(choices=audio_files, label="Select Audio File")
+
+# Define Gradio interface components for both tabs
+with gr.Blocks() as demo:
+    gr.Markdown("## ML Speech Emotion Detection")
+    gr.Markdown("Speechbrain powered wav2vec 2.0 pretrained model on IEMOCAP dataset.")
+
+    with gr.Tabs():
+        with gr.TabItem("Upload Audio"):
+            with gr.Group():
+                audio_upload = gr.Audio(label="Upload Audio", type="file")
+                submit_btn_1 = gr.Button("Classify Uploaded Audio")
+            audio_player_1 = gr.Audio(label="Uploaded Audio Player", interactive=True)
+            output_text_1 = gr.Textbox(label="Prediction")
+
+            submit_btn_1.click(predict_emotion_upload, inputs=audio_upload, outputs=[output_text_1, audio_player_1])
+
+        with gr.TabItem("Select from List"):
+            with gr.Group():
+                submit_btn_2 = gr.Button("Classify Selected Audio")
+            audio_player_2 = gr.Audio(label="Selected Audio Player", interactive=True)
+            output_text_2 = gr.Textbox(label="Prediction")
+
+            audio_files_dropdown.change(create_audio_player, inputs=audio_files_dropdown, outputs=audio_player_2)
+            submit_btn_2.click(predict_emotion_select, inputs=audio_files_dropdown, outputs=output_text_2)
+
+demo.launch()