Create app.py

app.py

@@ -0,0 +1,43 @@
+import cv2
+import numpy as np
+import gradio as gr
+import tensorflow as tf
+from huggingface_hub import hf_hub_download
+
+# Load the model from Hugging Face Model Hub
+model_path = hf_hub_download(repo_id="sign_language", filename="saved_model.pb", repo_type="model")
+model = tf.saved_model.load(model_path)
+infer = model.signatures["serving_default"]
+
+# Define class labels (modify as per your dataset)
+class_labels = ['Hello', 'Yes', 'No', 'Thank You', 'Please']
+
+def predict_sign(frame):
+    # Preprocess the frame
+    img = cv2.resize(frame, (224, 224))  # Resize to match model input
+    img = img / 255.0  # Normalize
+    img = np.expand_dims(img, axis=0)  # Add batch dimension
+    img = tf.convert_to_tensor(img, dtype=tf.float32)
+    
+    # Make prediction
+    predictions = infer(tf.constant(img))
+    output_tensor_name = list(predictions.keys())[0]  # Get the output tensor name
+    predictions = predictions[output_tensor_name].numpy()
+    predicted_class = class_labels[np.argmax(predictions)]
+    confidence = np.max(predictions)
+    
+    return predicted_class, confidence
+
+def process_frame(frame):
+    pred, conf = predict_sign(frame)
+    cv2.putText(frame, f"{pred} ({conf:.2f})", (10, 50), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+    return frame
+
+# Gradio Live Webcam Interface
+def webcam_feed():
+    return gr.Video(source="webcam", streaming=True, mirror=True)
+
+gui = gr.Interface(fn=process_frame, inputs=webcam_feed(), outputs="image", live=True)
+
+if __name__ == "__main__":
+    gui.launch(server_name="0.0.0.0", server_port=7860)