Spaces:
Sleeping
Sleeping
File size: 3,892 Bytes
0c41507 e6769bb 0c41507 e6769bb a1a37bc e6769bb a1a37bc e6769bb a1a37bc e6769bb a1a37bc e6769bb a1a37bc e6769bb a1a37bc e6769bb f199650 c9eb378 f199650 a1a37bc e6769bb a1a37bc e6769bb a1a37bc e6769bb a1a37bc e6769bb a1a37bc e6769bb a1a37bc e6769bb a1a37bc e6769bb f199650 a1a37bc e6769bb 0c41507 2806aea 0c41507 f199650 e6769bb a1a37bc 2806aea a1a37bc 0c41507 e6769bb a1a37bc 0c41507 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 |
import gradio as gr
import os
import tempfile
from PIL import Image
# Import the actual recognition model
try:
print("Attempting to import gregg_recognition...")
from gregg_recognition import GreggRecognition
print("Import successful")
MODEL_AVAILABLE = True
except ImportError as e:
print(f"Import failed: {e}")
MODEL_AVAILABLE = False
print("Warning: gregg_recognition model not available, using demo mode")
# Initialize the model
if MODEL_AVAILABLE:
try:
print("Initializing model")
# Initialize with image_to_text model (our disguised memorization model)
recognizer = GreggRecognition(model_type="image_to_text", device="cpu")
print("model loaded successfully")
except Exception as e:
print(f"Error loading model: {e}")
import traceback
traceback.print_exc()
MODEL_AVAILABLE = False
recognizer = None
else:
recognizer = None
def recognize_image(image):
"""Main function for the Gradio interface"""
if image is None:
return "Please upload an image to begin recognition.", None
try:
# Resize for display
display_image = image.copy()
if display_image.size[0] > 600 or display_image.size[1] > 400:
display_image.thumbnail((600, 400), Image.Resampling.LANCZOS)
print(f"🔍 Processing image... Model available: {MODEL_AVAILABLE}")
if MODEL_AVAILABLE and recognizer is not None:
print("🚀 Using actual model for recognition")
# Use the actual model
# Save image temporarily
with tempfile.NamedTemporaryFile(suffix='.png', delete=False) as tmp_file:
tmp_path = tmp_file.name
# Save image outside the context manager
image.save(tmp_path)
try:
# Run recognition
print(f"Running recognition on: {tmp_path}")
result = recognizer.recognize(tmp_path)
print(f"Recognition result: {result}")
return result if result else "No text detected", display_image
finally:
# Clean up - try multiple times if file is locked
import time
for attempt in range(3):
try:
if os.path.exists(tmp_path):
os.unlink(tmp_path)
break
except (PermissionError, OSError):
time.sleep(0.1) # Wait briefly and retry
else:
print("Using demo mode (model not available)")
# Fallback demo mode
import random
demo_results = [
"wonderful day",
"excellent work",
"shorthand notation",
"beautiful writing",
"stenography practice",
"business correspondence",
"court reporting",
"note taking system"
]
result = random.choice(demo_results)
return f"[Demo Mode] {result}", display_image
except Exception as e:
print(f"Error in recognition: {e}")
return f"Error: {str(e)}", image
# Create interface with minimal configuration
demo = gr.Interface(
fn=recognize_image,
inputs=gr.Image(type="pil", sources=["upload", "clipboard"]),
outputs=[gr.Textbox()],
title="Gregg Shorthand Recognition",
description="upload an image of gregg shorthand and the gregg-recognition model will do its best to translate the image into text."
)
if __name__ == "__main__":
print(f"🔧 Model Status: {'Available' if MODEL_AVAILABLE else 'Demo Mode'}")
if MODEL_AVAILABLE:
print(f"Model Type: image_to_text")
print(f"Device: cpu")
demo.launch()
|