Duplicate from arcma/decap

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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

Dockerfile

@@ -0,0 +1,15 @@
+FROM python:3.9
+
+RUN useradd -m -u 1000 user
+USER user
+WORKDIR /home/user
+
+COPY ./requirements.txt /home/user/requirements.txt
+
+RUN pip3 install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cpu
+RUN pip install --no-cache-dir --upgrade -r /home/user/requirements.txt
+
+COPY --chown=user . .
+CMD chmod -R 777 /home/user
+
+CMD ["python", "run.py"]

README.md

@@ -0,0 +1,11 @@
+---
+title: Decap
+emoji: 😻
+colorFrom: indigo
+colorTo: yellow
+sdk: docker
+pinned: false
+duplicated_from: arcma/decap
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

requirements.txt

@@ -0,0 +1,8 @@
+requests
+transformers
+torch
+Pillow
+flask
+werkzeug
+sentencepiece
+protobuf==3.20.0

run.py

@@ -0,0 +1,71 @@
+import requests
+import base64
+import io
+from transformers import TrOCRProcessor, VisionEncoderDecoderModel
+from PIL import Image
+import torch
+import time
+
+processor = TrOCRProcessor.from_pretrained("arcma/decap")
+model = VisionEncoderDecoderModel.from_pretrained("arcma/decap")
+model.eval()
+# torch.compile(model)
+
+def check(x):
+    if len(x) < 6:
+        return False
+    if not set(x).issubset('1234567890abcdefghijklmnopqrstuvwxyz'):
+        return False
+    return True
+
+def process_image(image):
+    pixel_values = processor(image, return_tensors="pt").pixel_values
+    with torch.no_grad():
+        generated_ids = model.generate(pixel_values, num_beams=4, num_return_sequences=4)
+    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
+    generated_text = [x for x in generated_text if check(x)]
+    return generated_text[0]
+
+def process_html(html):
+    
+    orig_im = Image.open(
+        io.BytesIO(
+            base64.b64decode(
+                html
+                .partition('''" style="background:white url('data:image/jpg;base64,''')[2]
+                .partition("') no-repeat")[0]
+            )
+        )
+    )
+    
+    return process_image(orig_im)
+
+
+
+from werkzeug.wrappers import Request, Response
+from flask import Flask, request
+from flask import jsonify
+
+app = Flask(__name__)
+
+@app.route("/", methods=['POST', 'OPTIONS'])
+def hello():
+    try:
+        return jsonify({
+            'x': process_html(request.json['data'])
+        })
+    except:
+        print('fail')
+    return "Hello World!"
+
+@app.after_request
+def after_request(response):
+    response.headers.add("Access-Control-Allow-Origin", "*")
+    response.headers.add("Access-Control-Allow-Credentials", "true")
+    response.headers.add("Access-Control-Allow-Methods", "GET,HEAD,OPTIONS,POST,PUT")
+    response.headers.add("Access-Control-Allow-Headers", "Access-Control-Allow-Headers, Origin,Accept, X-Requested-With, Content-Type, Access-Control-Request-Method, Access-Control-Request-Headers")
+    return response
+
+if __name__ == '__main__':
+    from werkzeug.serving import run_simple
+    run_simple('0.0.0.0', 7860, app)