Text Captioner

app.py

@@ -0,0 +1,42 @@
+API_URL = "https://api-inference.huggingface.co/models/Salesforce/blip-image-captioning-base"
+
+# Helper functions
+import requests, json
+
+#Image-to-text endpoint
+def get_completion(inputs, parameters=None, ENDPOINT_URL=API_URL): 
+    hf_api_key = "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"
+    headers = {
+      "Content-Type": "application/json"
+    }
+    data = { "inputs": inputs }
+    if parameters is not None:
+        data.update({"parameters": parameters})
+    response = requests.request("POST",
+                                ENDPOINT_URL,
+                                headers=headers,
+                                data=json.dumps(data))
+    return json.loads(response.content.decode("utf-8"))
+import gradio as gr 
+
+def image_to_base64_str(pil_image):
+    byte_arr = io.BytesIO()
+    pil_image.save(byte_arr, format='PNG')
+    byte_arr = byte_arr.getvalue()
+    return str(base64.b64encode(byte_arr).decode('utf-8'))
+
+def captioner(image):
+    base64_image = image_to_base64_str(image)
+    result = get_completion(base64_image)
+    return result[0]['generated_text']
+
+gr.close_all()
+demo = gr.Interface(fn=captioner,
+                    inputs=[gr.Image(label="Upload image", type="pil")],
+                    outputs=[gr.Textbox(label="Caption")],
+                    title="Image Captioning with BLIP",
+                    description="Caption any image using the BLIP model",
+                    allow_flagging="never",
+                    examples=["/kaggle/input/images/dry land.jpg", "/kaggle/input/images/hills.jpg", "/kaggle/input/images/house.jpg"])
+
+demo.launch(inline=False)