update

main.py

@@ -5,8 +5,15 @@ from transformers import pipeline
 
 app = FastAPI()
 
-pipe_ocr = pipeline("text0recognition", model="naver-clova-ocr/bros-base-uncased")
 
+from transformers import pipeline
+
+image_to_text = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
+
+
+# [{'generated_text': 'a soccer game with a player jumping to catch the ball '}]
+
+model = AutoModelForSeq2SeqLM.from_pretrained("google/pix2struct-ocrvqa-large")
 app.mount("/", StaticFiles(directory="static", html=True), name="static")
 
 @app.get("/")
@@ -15,5 +22,5 @@ def index() -> FileResponse:
 
 @app.get("/ocr")
 def ocr(input):
-    result = pipe_ocr(input)
+    result = image_to_text(input)
     print(result)