Duplicate from ysharma/nougat

Co-authored-by: yuvraj sharma <ysharma@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+output/nougat.pdf filter=lfs diff=lfs merge=lfs -text
+input/nougat.pdf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Nougat
+emoji: 👁📄
+colorFrom: pink
+colorTo: pink
+sdk: gradio
+sdk_version: 3.41.2
+app_file: app.py
+license: mit
+duplicated_from: ysharma/nougat
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,158 @@
+import gradio as gr
+import subprocess
+import uuid
+import os
+import requests
+import re
+
+
+def get_pdf(pdf_link):
+  # Generate a unique filename
+  unique_filename = f"input/downloaded_paper_{uuid.uuid4().hex}.pdf"
+
+  # Send a GET request to the PDF link
+  response = requests.get(pdf_link)
+
+  if response.status_code == 200:
+      # Save the PDF content to a local file
+      with open(unique_filename, 'wb') as pdf_file:
+          pdf_file.write(response.content)
+      print("PDF downloaded successfully.")
+  else:
+      print("Failed to download the PDF.")
+  return unique_filename #.split('/')[-1][:-4]
+
+
+def nougat_ocr(file_name):
+
+  #unique_filename = f"/content/output/downloaded_paper_{uuid.uuid4().hex}.pdf"
+  # Command to run
+  cli_command = [
+      'nougat',
+      #'--out', unique_filename,
+      '--out', 'output',
+      'pdf', f'{file_name}',
+      '--checkpoint', 'nougat',
+      '--markdown'
+  ]
+
+  # Run the command and capture its output
+  #completed_process = 
+  subprocess.run(cli_command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
+
+  return #unique_filename
+
+
+def predict(pdf_file, pdf_link):
+  if pdf_file is None:
+    if pdf_link == '':
+      print("No file is uploaded and No link is provided")
+      return "No data provided. Upload a pdf file or provide a pdf link and try again!"
+    else:
+      print(f'pdf_link is - {pdf_link}')
+      file_name = get_pdf(pdf_link)
+      print(f'file_name is - {file_name}')
+  else:
+    file_name = pdf_file.name
+    print(file_name)
+    pdf_name = pdf_file.name.split('/')[-1].split('.')[0]
+    print(pdf_name)
+
+  # Call nougat
+  nougat_ocr(file_name)
+  #print("BACKKKK")
+
+  # Open the file for reading
+  file_name = file_name.split('/')[-1][:-4]
+  with open(f'output/{file_name}.mmd', 'r') as file:
+      content = file.read()
+  # switch math delimiters
+  content = content.replace(r'\(', '$').replace(r'\)', '$').replace(r'\[', '$$').replace(r'\]', '$$')
+  return content
+
+
+
+
+def nougat_ocr1(file_name):
+  print('******* inside nougat_ocr *******')
+  # CLI Command to run
+  cli_command = [
+      'nougat',
+      '--out', 'output',
+      'pdf', f'{file_name}',
+      '--checkpoint', 'nougat',
+      '--markdown'
+  ]
+
+  # Run the command and get .mmd file in an output folder
+  subprocess.run(cli_command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
+  return
+
+
+def predict1(pdf_file):
+  print('******* inside predict *******')
+  print(f"temporary file - {pdf_file.name}")
+  pdf_name = pdf_file.name.split('/')[-1].split('.')[0]
+  print(f"pdf file name - {pdf_name}")
+    
+  #! Get prediction for a PDF using nougat
+  nougat_ocr(pdf_file.name)
+  print("BAACCKKK")
+  
+  # Open the multimarkdown (.mmd) file for reading
+  with open(f'output/{pdf_name}.mmd', 'r') as file:
+      content = file.read() 
+      
+  return content
+
+def process_example(pdf_file,pdf_link):
+ ocr_content = predict(pdf_file,pdf_link)
+ return gr.update(value=ocr_content)
+      
+css = """
+  #mkd {
+    height: 500px; 
+    overflow: auto; 
+    border: 1px solid #ccc; 
+  }
+"""
+
+with gr.Blocks(css=css) as demo:
+  gr.HTML("<h1><center>Nougat: Neural Optical Understanding for Academic Documents<center><h1>")
+  gr.HTML("<h3><center>Lukas Blecher et al. <a href='https://arxiv.org/pdf/2308.13418.pdf' target='_blank'>Paper</a>, <a href='https://facebookresearch.github.io/nougat/'>Project</a><center></h3>")
+
+  with gr.Row():
+    mkd = gr.Markdown('<h4><center>Upload a PDF</center></h4>',scale=1)
+    mkd = gr.Markdown('<h4><center><i>OR</i></center></h4>',scale=1)
+    mkd = gr.Markdown('<h4><center>Provide a PDF link</center></h4>',scale=1)
+  
+  with gr.Row(equal_height=True):
+    pdf_file = gr.File(label='PDF📃', file_count='single', scale=1)
+    pdf_link = gr.Textbox(placeholder='Enter an Arxiv link here', label='PDF link🔗🌐', scale=1)
+
+  with gr.Row():
+    btn = gr.Button('Run NOUGAT🍫')
+    clr = gr.Button('Clear🚿')
+
+  output_headline = gr.Markdown("<h3>PDF converted to markup language through Nougat-OCR👇:</h3>")
+  parsed_output = gr.Markdown(elem_id='mkd', value='📃🔤OCR Output')
+  
+  btn.click(predict, [pdf_file, pdf_link], parsed_output )
+  clr.click(lambda : (gr.update(value=None), 
+                      gr.update(value=None),
+                      gr.update(value=None)), 
+             [], 
+             [pdf_file, pdf_link, parsed_output]
+            )
+
+  gr.Examples(
+      [["input/nougat.pdf", ""], [None, "https://arxiv.org/pdf/2308.08316.pdf"]],
+      inputs = [pdf_file, pdf_link],
+      outputs = parsed_output,
+      fn=process_example,
+      cache_examples=True,
+      label='Click on any Examples below to get Nougat OCR results quickly:'
+  )
+    
+demo.queue()
+demo.launch(debug=True)

input/nougat.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:679be336ce8010d3dc86b9530f0a30d4d5ea2a13153c6f274601b40f4382745b
+size 4133781

nougat/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "/fsx-llm/lblecher/checkpoints/nougat/small/20230426_125023",
+  "align_long_axis": false,
+  "architectures": [
+    "NougatModel"
+  ],
+  "decoder_layer": 4,
+  "embed_dim": 128,
+  "encoder_layer": [
+    2,
+    2,
+    14,
+    2
+  ],
+  "hidden_dimension": 1024,
+  "input_size": [
+    896,
+    672
+  ],
+  "max_length": 3584,
+  "max_position_embeddings": 3584,
+  "model_type": "nougat",
+  "num_heads": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "patch_size": 4,
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "window_size": 7
+}

nougat/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfca8831ad5e81fcd96b66f207934f2aaac4e8996449619515c58267c5e03686
+size 1002629505

nougat/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

nougat/tokenizer_config.json

@@ -0,0 +1,4 @@
+{
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

output/nougat.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:679be336ce8010d3dc86b9530f0a30d4d5ea2a13153c6f274601b40f4382745b
+size 4133781

requirements.txt

@@ -0,0 +1 @@
+nougat-ocr