Update main.py

main.py

@@ -1,17 +1,13 @@
 import os
-
-# os.system("sudo apt-get install xclip")
-
-import nltk
-import pyclip
-import pytesseract
-from nltk.tokenize import sent_tokenize
-from transformers import MarianMTModel, MarianTokenizer
-# Newly added below
 from fastapi import FastAPI, File, UploadFile, Body, Depends, HTTPException
 from fastapi.security.api_key import APIKeyHeader
 from typing import Optional
 from fastapi.encoders import jsonable_encoder
+from PIL import Image
+from io import BytesIO
+import pytesseract
+from nltk.tokenize import sent_tokenize
+from transformers import MarianMTModel, MarianTokenizer
 
 API_KEY = os.environ.get("API_KEY")
 
@@ -29,39 +25,36 @@ async def ocr(
     image: UploadFile = File(...),
     languages: list = Body(["eng"])
 ):
-    # if api_key != API_KEY:
-    #     return {"error": "Invalid API key"}, 401
-
     try:
-        text = image_to_string(await image.read(), lang="+".join(languages))
+        content = await image.read()
+        image = Image.open(BytesIO(content))
+        text = pytesseract.image_to_string(image, lang="+".join(languages))
     except Exception as e:
         return {"error": str(e)}, 500
 
     return jsonable_encoder({"text": text})
 
+@app.post("/api/translate", response_model=dict)
+async def translate(
+    api_key: str = Depends(get_api_key),
+    text: str = Body(...),
+    src: str = "en",
+    trg: str = "zh",
+):
+    if api_key != API_KEY:
+        return {"error": "Invalid API key"}, 401
 
-#@app.post("/api/translate", response_model=dict)
-#async def translate(
-    #api_key: str = Depends(get_api_key),
-    #text: str = Body(...),
-    #src: str = "en",
-    #trg: str = "zh",
-#):
-    # if api_key != API_KEY:
-    #     return {"error": "Invalid API key"}, 401
-
-   # tokenizer, model = get_model(src, trg)
-
-   # translated_text = ""
-   # for sentence in sent_tokenize(text):
-    #    translated_sub = model.generate(**tokenizer(sentence, return_tensors="pt"))[0]
-     #   translated_text += tokenizer.decode(translated_sub, skip_special_tokens=True) + "\n"
+    tokenizer, model = get_model(src, trg)
 
-   # return jsonable_encoder({"translated_text": translated_text})
+    translated_text = ""
+    for sentence in sent_tokenize(text):
+        translated_sub = model.generate(**tokenizer(sentence, return_tensors="pt"))[0]
+        translated_text += tokenizer.decode(translated_sub, skip_special_tokens=True) + "\n"
 
+    return jsonable_encoder({"translated_text": translated_text})
 
-#def get_model(src: str, trg: str):
-   # model_name = f"Helsinki-NLP/opus-mt-{src}-{trg}"
-    #tokenizer = MarianTokenizer.from_pretrained(model_name)
-    #model = MarianMTModel.from_pretrained(model_name)
-    #return tokenizer, model
+def get_model(src: str, trg: str):
+    model_name = f"Helsinki-NLP/opus-mt-{src}-{trg}"
+    tokenizer = MarianTokenizer.from_pretrained(model_name)
+    model = MarianMTModel.from_pretrained(model_name)
+    return tokenizer, model