Update the interface completely

app.py

@@ -1,7 +1,66 @@
+# AUTOGENERATED! DO NOT EDIT! 
+
+# %% auto 0
+__all__ = ['learn', 'categories', 'audio', 'label', 'inf', 'extract_emotion', 'get_y', 'classify_audio']
+
+from fastai.vision.all import *
 import gradio as gr
+import matplotlib.pyplot as plt
+import librosa
+import librosa.display
+from pathlib import Path
+import os
+
+def extract_emotion(file_name: str) -> str:
+    """
+    Given the name of the file, return the label
+    indicating the emotion associated with the audio.
+    """
+    # Split the filename at each underscore
+    parts = file_name.split('_')
+    # Label is after second
+    label_with_extension = parts[-1]
+    # Remove the extension to get only the label
+    label = label_with_extension[:-4]
+    return label
+
+def get_y(filepath): return extract_emotion(str(filepath).split("/")[-1])
+
+# Load Learner
+learn = load_learner("emotion_model.pkl")
+categories = learn.dls.vocab
+
+def classify_audio(audio_file):
+  """
+  Takes the audio file and returns its
+  prediction of emotions along with probabilities.
+  """
+  # Load the audio file
+  sample, sample_rate = librosa.load(audio_file, sr=None, duration=20)
+  # Create spectogram
+  S = librosa.feature.melspectrogram(y=sample, sr=sample_rate)
+  S_DB = librosa.power_to_db(S, ref=np.max)
+  # Prepare the figure for saving the spectrogram
+  fig, ax = plt.subplots()
+  fig.tight_layout(pad=0)
+  # Create the spectogram image
+  img = librosa.display.specshow(S_DB, sr=sample_rate, x_axis='time',
+                                 y_axis='mel', ax=ax)
+  # Turn off the axis for saving
+  plt.axis('off')
+  # Save the spectogram temporarily
+  temp_img_path = Path("temp_spectogram.png")
+  plt.savefig(temp_img_path)
+
+  pred,idx, probs = learn.predict(temp_img_path)
+
+  # Remove the temporary spectogram image
+  os.remove(temp_img_path)
 
-def greet(name):
-    return "Hello " + name + "!!"
+  return dict(zip(categories, map(float, probs)))
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+audio = gr.Audio(type="filepath", label="Upload Audio <=20 seconds")
+label = gr.Label()
+# Gradio Interface
+inf = gr.Interface(fn=classify_audio, inputs=audio, outputs=label)
+inf.launch()