Duplicate from awacke1/AW-05-GR-NLP-Image2Text-Multilingual-OCR

Co-authored-by: Aaron C Wacker <awacke1@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,31 @@
+*.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
+*.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
+*.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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pb 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
+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

README.md

@@ -0,0 +1,14 @@
+---
+title: AW 05 GR NLP Image2Text Multilingual OCR
+emoji: 🚀
+colorFrom: purple
+colorTo: red
+sdk: gradio
+sdk_version: 3.4
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: awacke1/AW-05-GR-NLP-Image2Text-Multilingual-OCR
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,54 @@
+import pandas as pd
+import PIL
+from PIL import Image
+from PIL import ImageDraw
+import gradio as gr
+import torch
+import easyocr
+
+torch.hub.download_url_to_file('https://github.com/JaidedAI/EasyOCR/raw/master/examples/english.png', 'english.png')
+torch.hub.download_url_to_file('https://github.com/JaidedAI/EasyOCR/raw/master/examples/chinese.jpg', 'chinese.jpg')
+torch.hub.download_url_to_file('https://github.com/JaidedAI/EasyOCR/raw/master/examples/japanese.jpg', 'japanese.jpg')
+torch.hub.download_url_to_file('https://i.imgur.com/mwQFd7G.jpeg', 'Hindi.jpeg')
+
+def draw_boxes(image, bounds, color='yellow', width=2):
+    draw = ImageDraw.Draw(image)
+    for bound in bounds:
+        p0, p1, p2, p3 = bound[0]
+        draw.line([*p0, *p1, *p2, *p3, *p0], fill=color, width=width)
+    return image
+
+def inference(img, lang):
+    reader = easyocr.Reader(lang)
+    bounds = reader.readtext(img.name)
+    im = PIL.Image.open(img.name)
+    draw_boxes(im, bounds)
+    im.save('result.jpg')
+    return ['result.jpg', pd.DataFrame(bounds).iloc[: , 1:]]
+
+title = 'Image To Optical Character Recognition'
+description = 'Multilingual OCR which works conveniently on all devices in multiple languages.'
+article = "<p style='text-align: center'></p>"
+examples = [['english.png',['en']],['chinese.jpg',['ch_sim', 'en']],['japanese.jpg',['ja', 'en']],['Hindi.jpeg',['hi', 'en']]]
+css = ".output_image, .input_image {height: 40rem !important; width: 100% !important;}"
+choices = [
+    "ch_sim",
+    "ch_tra",
+    "de",
+    "en",
+    "es",
+    "ja",
+    "hi",
+    "ru"
+]
+gr.Interface(
+    inference,
+    [gr.inputs.Image(type='file', label='Input'),gr.inputs.CheckboxGroup(choices, type="value", default=['en'], label='language')],
+    [gr.outputs.Image(type='file', label='Output'), gr.outputs.Dataframe(headers=['text', 'confidence'])],
+    title=title,
+    description=description,
+    article=article,
+    examples=examples,
+    css=css,
+    enable_queue=True
+    ).launch(debug=True)

requirements.txt

@@ -0,0 +1,5 @@
+opencv-python-headless<4.3
+Pillow
+gradio
+torch
+easyocr