feat: adds english caption using blip model

app.py

@@ -0,0 +1,13 @@
+import gradio as gr
+from transformers import pipeline
+
+model_id = "Salesforce/blip-image-captioning-large"
+caption_eng = pipeline(model=model_id)
+
+def evaluate():
+    return caption_eng(input)[0]["generated_text"]
+
+iface = gr.Interface(fn=evaluate, inputs=gr.Image(type="pil"), outputs="text")
+
+if __name__ == "__main__":
+    iface.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+transformers
+torch