Initial commit for Arabic Dialect ID demo

app.py

@@ -0,0 +1,52 @@
+import gradio as gr
+from transformers import pipeline
+import numpy as np
+
+# Load the model
+model_id = "badrex/mms-300m-arabic-dialect-identifier"  # Replace with your model ID
+classifier = pipeline("audio-classification", model=model_id)
+
+# Define dialect names for better display
+dialect_mapping = {
+    "MSA": "Modern Standard Arabic",
+    "Egyptian": "Egyptian Arabic",
+    "Gulf": "Gulf Arabic",
+    "Levantine": "Levantine Arabic",
+    "Maghrebi": "Maghrebi Arabic"
+}
+
+def predict_dialect(audio, sr):
+    # Process the audio input
+    if len(audio.shape) > 1:
+        audio = audio.mean(axis=1)  # Convert stereo to mono
+    
+    # Classify the dialect
+    predictions = classifier({"sampling_rate": sr, "raw": audio})
+    
+    # Format results for display
+    results = {}
+    for pred in predictions:
+        dialect_name = dialect_mapping.get(pred['label'], pred['label'])
+        results[dialect_name] = float(pred['score'])
+    
+    return results
+
+# Create the Gradio interface
+demo = gr.Interface(
+    fn=predict_dialect,
+    inputs=gr.Audio(type="numpy", label="Upload or Record Audio"),
+    outputs=gr.Label(num_top_classes=5, label="Predicted Dialect"),
+    title="Arabic Dialect Identifier",
+    description="""This demo identifies Arabic dialects from speech audio.
+    Upload an audio file or record your voice speaking Arabic to see which dialect it matches.
+    The model identifies: Modern Standard Arabic (MSA), Egyptian, Gulf, Levantine, and Maghrebi dialects.""",
+    examples=[
+        # Optional: Add example audio files here if you have them
+        # ["examples/msa_example.wav"],
+        # ["examples/egyptian_example.wav"],
+    ],
+    allow_flagging="never"
+)
+
+# Launch the app
+demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+gradio>=3.50.2
+transformers>=4.36.0
+torch>=2.0.0
+librosa>=0.10.1