Create app.py

app.py

@@ -0,0 +1,141 @@
+import gradio as gr
+import torch
+import librosa
+from transformers import AutoModelForAudioClassification, AutoFeatureExtractor
+
+model = AutoModelForAudioClassification.from_pretrained(".")
+extractor = AutoFeatureExtractor.from_pretrained(".")
+
+maps = {
+    0:"blues",
+    1:"classical",
+    2:"country",
+    3:"disco",
+    4:"hiphop",
+    5:"jazz",
+    6:"metal",
+    7:"pop",
+    8:"reggae",
+    9:"rock"
+}
+
+def predict(audio):
+
+    audio, sr = librosa.load(audio, sr=16000)
+
+    inputs = extractor(audio, sampling_rate=16000, return_tensors="pt")
+
+    with torch.no_grad():
+        logits = model(**inputs).logits
+
+    probs = torch.softmax(logits, dim=-1)[0].tolist()
+
+    result = {maps[i]: float(probs[i]) for i in range(10)}
+
+    return result
+
+
+with gr.Blocks(title="AST_Audio_Classfication") as demo:
+
+    gr.Markdown("""
+    <div style="text-align:center;">
+        <h1 style="font-size:3rem;">🎵 Music Genre Detection</h1>
+        <p style="font-size:1.2rem; color:#555;">
+        Audio classification using <b>Audio Spectrogram Transformer (AST)</b><br>
+        Built as part of the <b>IIT Madras Intro to Deep Learning & GenAI Project (2026 Term 1)</b>
+        </p>
+    </div>
+    """)
+
+    with gr.Row():
+
+        with gr.Column(scale=1):
+
+            gr.HTML("""
+            <div style="
+                background:white;
+                padding:20px;
+                border-radius:14px;
+                box-shadow:0 2px 12px rgba(0,0,0,0.08);
+                margin-bottom:20px;
+            ">
+            <h2>📌 Model Overview</h2>
+            <ul style="line-height:1.6;">
+                <li><b>Architecture:</b> Audio Spectrogram Transformer</li>
+                <li><b>Base Model:</b> MIT AST</li>
+                <li><b>Task:</b> Music Genre Classification</li>
+                <li><b>Classes:</b> 10 Genres</li>
+                <li><b>Framework:</b> PyTorch + Hugging Face</li>
+            </ul>
+            </div>
+            """)
+
+            gr.HTML("""
+            <div style="
+                background:white;
+                padding:20px;
+                border-radius:14px;
+                box-shadow:0 2px 12px rgba(0,0,0,0.08);
+                margin-bottom:20px;
+            ">
+            <h2>🎧 Genres Detected by Model</h2>
+            <ul>
+                <li>🎷 Jazz</li>
+                <li>🎸 Rock</li>
+                <li>🎤 Pop</li>
+                <li>🎶 Blues</li>
+                <li>🎼 Classical</li>
+                <li>🤠 Country</li>
+                <li>💃 Disco</li>
+                <li>🔥 HipHop</li>
+                <li>🎛 Metal</li>
+                <li>🌴 Reggae</li>
+            </ul>
+            </div>
+            """)
+
+            gr.HTML("""
+            <div style="
+                background:white;
+                padding:20px;
+                border-radius:14px;
+                box-shadow:0 2px 12px rgba(0,0,0,0.08);
+            ">
+            <h2>🎓 Project Info</h2>
+            <ul style="line-height:1.6;">
+                <li><b>Course:</b> Deep Learning & Generative AI</li>
+                <li><b>Institution:</b> IIT Madras</li>
+                <li><b>Term:</b> 2026 Term 1</li>
+                <li><b>Student:</b> Ayusman Samasi</li>
+                <li><b>Roll:</b> 22f3001XXX</li>
+                <li><b>Email:</b> 22f3001XXX@ds.study.iitm.ac.in</li>
+            </ul>
+            </div>
+            """)
+
+        with gr.Column(scale=2):
+
+            audio_input = gr.Audio(
+                sources=["upload","microphone"],
+                type="filepath",
+                label="Upload or Record Audio"
+            )
+
+            btn = gr.Button("🎯 Detect Genre")
+
+            output = gr.Label(
+                num_top_classes=5,
+                label="Prediction Probabilities"
+            )
+
+            btn.click(predict, inputs=audio_input, outputs=output)
+
+    gr.Markdown("""
+    <br>
+    <p style="text-align:center; color:#777;">
+    Built with ❤️ using Hugging Face Transformers & Gradio<br>
+    <b>Ayusman Samasi • IIT Madras DL & GenAI Project T1 2026</b>
+    </p>
+    """)
+
+demo.launch()