Update appImage.py

appImage.py

@@ -1,60 +1,32 @@
-
-from fastapi import FastAPI
-from fastapi.responses import RedirectResponse, JSONResponse, FileResponse
-import os
+# appImage.py
+from transformers import pipeline
+import tempfile, os
 from PIL import Image
-from transformers import ViltProcessor, ViltForQuestionAnswering, pipeline
 from gtts import gTTS
-import easyocr
-import torch
-import tempfile
-import numpy as np
-from io import BytesIO
-
-app = FastAPI()
 
-vqa_processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
-vqa_model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
 captioner = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
-reader = easyocr.Reader(['en', 'fr'])
-
-def classify_question(question: str):
-    q = question.lower()
-    if any(w in q for w in ["text", "say", "written", "read"]):
-        return "ocr"
-    if any(w in q for w in ["caption", "describe", "what is in the image"]):
-        return "caption"
-    return "vqa"
-
-def answer_question_from_image(image, question):
-    if image is None or not question.strip():
-        return "Please upload an image and ask a question.", None
 
-    mode = classify_question(question)
+async def caption_image(file):
+    contents = await file.read()
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".png") as tmp:
+        tmp.write(contents)
+        image_path = tmp.name
 
-    try:
-        if mode == "ocr":
-            result = reader.readtext(np.array(image))
-            answer = " ".join([entry[1] for entry in result]) or "No readable text found."
-
-        elif mode == "caption":
-            answer = captioner(image)[0]['generated_text']
+    captions = captioner(image_path)
+    caption = captions[0]['generated_text'] if captions else "No caption generated."
 
-        else:
-            inputs = vqa_processor(image, question, return_tensors="pt")
-            with torch.no_grad():
-                outputs = vqa_model(**inputs)
-            predicted_id = outputs.logits.argmax(-1).item()
-            answer = vqa_model.config.id2label[predicted_id]
+    audio_path = text_to_speech(caption)
 
-        tts = gTTS(text=answer)
-        with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp:
-            tts.save(tmp.name)
-            return answer, tmp.name
+    result = {"caption": caption}
+    if audio_path:
+        result["audioUrl"] = f"/files/{os.path.basename(audio_path)}"
+    return result
 
-    except Exception as e:
-        return f"Error: {e}", None
-
-@app.get("/")
-def home():
-    return RedirectResponse(url="/templates/home.html")
+def text_to_speech(text: str):
+    try:
+        tts = gTTS(text)
+        temp_audio = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
+        tts.save(temp_audio.name)
+        return temp_audio.name
+    except:
+        return ""