Spaces:
Running
Running
File size: 1,048 Bytes
145d936 658b64e 9bdea1a 145d936 a9d0472 145d936 9bdea1a 145d936 a9d0472 145d936 61f316a 145d936 |
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 |
import spaces
import gradio as gr
from marker.convert import convert_single_pdf
from marker.models import load_all_models
import surya.detection as detection
model_lst = load_all_models()
# Monkey patch to prevent spawning processes
def batch_text_detection(images, model, processor, batch_size=None):
preds, orig_sizes = detection.batch_detection(
images, model, processor, batch_size=batch_size
)
results = []
for i in range(len(images)):
result = detection.parallel_get_lines(preds[i], orig_sizes[i])
results.append(result)
return results
detection.batch_text_detection = batch_text_detection
@spaces.GPU
def convert(file_path):
print(file_path)
global model_lst
full_text, images = convert_single_pdf(
file_path,
model_lst,
max_pages=None,
langs=None,
batch_multiplier=16,
)
return full_text
gr.Interface(
convert,
inputs=gr.File(label="PDF file", type="filepath"),
outputs=gr.Markdown(label="Markdown"),
).launch()
|