Create app.py

app.py

@@ -0,0 +1,39 @@
+import gradio as gr
+import torch
+from transformers import Wav2Vec2ForSequenceClassification, Wav2Vec2Processor
+import librosa
+
+# Placeholder model (Replace later with your trained model)
+MODEL_NAME = "facebook/wav2vec2-base-960h"
+
+# Load the pre-trained model and processor
+processor = Wav2Vec2Processor.from_pretrained(MODEL_NAME)
+model = Wav2Vec2ForSequenceClassification.from_pretrained(MODEL_NAME)
+
+# Function to process audio input
+def classify_audio(audio_file):
+    # Load the audio file
+    speech, sr = librosa.load(audio_file, sr=16000)
+
+    # Preprocess with Hugging Face's feature extractor
+    inputs = processor(speech, sampling_rate=16000, return_tensors="pt", padding=True, truncation=True)
+
+    # Make predictions
+    with torch.no_grad():
+        logits = model(**inputs).logits
+
+    predicted_class_id = torch.argmax(logits, dim=-1).item()
+    return f"Predicted Class: {predicted_class_id}"
+
+# Gradio Interface
+interface = gr.Interface(
+    fn=classify_audio,
+    inputs=gr.Audio(source="upload", type="filepath"),
+    outputs="text",
+    title="Wav2Vec2 Audio Classification",
+    description="Upload an audio file, and the model will classify it."
+)
+
+# Launch the Gradio demo
+if __name__ == "__main__":
+    interface.launch()