Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -4,6 +4,20 @@ from transformers import AutoModel, AutoTokenizer
|
|
| 4 |
from pdf2image import convert_from_path
|
| 5 |
import torch
|
| 6 |
import os
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
|
| 8 |
# Load the OCR model
|
| 9 |
tokenizer = AutoTokenizer.from_pretrained("ucaslcl/GOT-OCR2_0", trust_remote_code=True)
|
|
|
|
| 4 |
from pdf2image import convert_from_path
|
| 5 |
import torch
|
| 6 |
import os
|
| 7 |
+
import os
|
| 8 |
+
import subprocess
|
| 9 |
+
import streamlit as st
|
| 10 |
+
import google.generativeai as genai
|
| 11 |
+
from transformers import AutoModel, AutoTokenizer
|
| 12 |
+
from pdf2image import convert_from_path
|
| 13 |
+
import torch
|
| 14 |
+
|
| 15 |
+
# Ensure Poppler is installed
|
| 16 |
+
def install_poppler():
|
| 17 |
+
if not os.path.exists("/usr/bin/pdftoppm"): # Check if Poppler is installed
|
| 18 |
+
st.warning("Installing Poppler for PDF processing...")
|
| 19 |
+
subprocess.run(["apt-get", "update"])
|
| 20 |
+
subprocess.run(["apt-get", "install", "-y", "poppler-utils"])
|
| 21 |
|
| 22 |
# Load the OCR model
|
| 23 |
tokenizer = AutoTokenizer.from_pretrained("ucaslcl/GOT-OCR2_0", trust_remote_code=True)
|