Update app.py

app.py

@@ -3,7 +3,7 @@ import torch
 import torchaudio
 from transformers import AutoFeatureExtractor, AutoModelForAudioClassification
 
-# Load the Hugging Face feature extractor and model
+# Load the HF feature extractor and model
 feature_extractor = AutoFeatureExtractor.from_pretrained(
     "MelodyMachine/Deepfake-audio-detection-V2"
 )
@@ -12,21 +12,21 @@ model = AutoModelForAudioClassification.from_pretrained(
 )
 
 def detect_deepfake_audio(audio_path: str) -> str:
-    # Load any audio format via torchaudio
+    # Load audio file
     waveform, sample_rate = torchaudio.load(audio_path)
 
-    # Convert to mono if stereo
+    # Mix to mono if necessary
     if waveform.shape[0] > 1:
         waveform = torch.mean(waveform, dim=0, keepdim=True)
 
-    # Preprocess for model
+    # Prepare inputs
     inputs = feature_extractor(
         waveform, sampling_rate=sample_rate, return_tensors="pt"
     )
     with torch.no_grad():
         outputs = model(**inputs)
 
-    # Softmax to get class probabilities
+    # Compute probabilities
     probs = torch.softmax(outputs.logits, dim=-1)[0]
     idx = torch.argmax(probs).item()
     label = model.config.id2label[idx]
@@ -34,11 +34,11 @@ def detect_deepfake_audio(audio_path: str) -> str:
 
     return f"The audio is classified as **{label}** with confidence **{confidence:.2f}**"
 
-# Gradio UI
+# Build the Gradio Blocks interface
 with gr.Blocks() as demo:
     gr.Markdown("# Audio Deepfake Detection")
     gr.Markdown("Upload an audio clip to check for deepfake content.")
-    audio_in = gr.Audio(source="upload", type="filepath", label="Audio File")
+    audio_in = gr.Audio(type="filepath", label="Select Audio File")
     txt_out = gr.Textbox(label="Result")
     gr.Button("Detect").click(
         fn=detect_deepfake_audio, inputs=audio_in, outputs=txt_out