Duplicate from gryan-galario/manga-ocr-demo

Co-authored-by: Gryan Carl Galario <[email protected]>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin 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
+*.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
+*.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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Manga Ocr Demo
+emoji: 💻
+colorFrom: indigo
+colorTo: purple
+sdk: gradio
+sdk_version: 2.8.14
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: gryan-galario/manga-ocr-demo
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference

app.py

@@ -0,0 +1,45 @@
+import re
+import jaconv
+import gradio as gr
+from transformers import AutoTokenizer, AutoFeatureExtractor, VisionEncoderDecoderModel
+from PIL import Image
+import torch
+
+
+tokenizer = AutoTokenizer.from_pretrained("kha-white/manga-ocr-base")
+
+model = VisionEncoderDecoderModel.from_pretrained("kha-white/manga-ocr-base")
+
+feature_extractor = AutoFeatureExtractor.from_pretrained("kha-white/manga-ocr-base")
+
+examples = ["00.jpg", "01.jpg", "02.jpg", "03.jpg", "04.jpg", "05.jpg", "06.jpg", "07.jpg", "08.jpg", "09.jpg", "10.jpg", "11.jpg"]
+
+def post_process(text):
+  text = ''.join(text.split())
+  text = text.replace('…', '...')
+  text = re.sub('[・.]{2,}', lambda x: (x.end() - x.start()) * '.', text)
+  text = jaconv.h2z(text, ascii=True, digit=True)
+  return text
+
+def manga_ocr(img):
+  img = img.convert('L').convert('RGB')
+  pixel_values = feature_extractor(img, return_tensors="pt").pixel_values
+  output = model.generate(pixel_values)[0]
+  text = tokenizer.decode(output, skip_special_tokens=True)
+  text = post_process(text)
+  return text
+
+iface = gr.Interface(
+    fn=manga_ocr,
+    inputs=[gr.inputs.Image(label="Input", type="pil")],
+    outputs="text",
+    layout="horizontal",
+    theme="huggingface",
+    title="Manga OCR",
+    description="Optical Character Recognization for Japanese Texts with focus on Mangas. The model is trained by kha-white with Github link: <a href=\"https://github.com/kha-white/manga-ocr\">manga-ocr</a> while the Space App is made by me.",
+    allow_flagging='never',
+    examples=examples,
+    article = "Author: <a href=\"https://huggingface.co/gryan-galario\">Gryan Galario</a>",
+)
+
+iface.launch()

requirements.txt

@@ -0,0 +1,10 @@
+fire
+fugashi
+jaconv
+loguru
+numpy
+Pillow
+pyperclip
+torch>=1.0
+transformers>=4.12.5
+unidic_lite