Update app.py

app.py

@@ -1,19 +1,28 @@
 from speechbrain.pretrained.interfaces import foreign_class
-import gradio as gr
 
 import warnings
 warnings.filterwarnings("ignore")
 
+import os
+import gradio as gr
+
+# Путь к каталогу с предзаписанными аудиофайлами
+prerecorded_audio_path = 'prerecorded'
+# 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]
+
 # 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',
@@ -21,13 +30,33 @@ emotion_dict = {
     'neu': 'Neutral'
 }
 
-def predict_emotion(audio):
-    out_prob, score, index, text_lab = learner.classify_file(audio.name)
-    return emotion_dict[text_lab[0]]
+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)
 
-# Loading gradio interface
-inputs = gr.inputs.Audio(label="Input Audio", type="file")
-outputs = "text"
 title = "ML Speech Emotion Detection"
-description = "Speechbrain powered wav2vec 2.0 pretrained model on IEMOCAP dataset using Gradio."
-gr.Interface(predict_emotion, inputs, outputs, title=title, description=description).launch()
+description = "Detect emotions from speech using a Speechbrain powered model."
+
+gr.Interface(fn=predict_emotion, inputs=inputs, outputs=outputs, title=title, description=description).launch()