Duplicate from priyank-m/vit-bert-ocr

Co-authored-by: priyank <priyank-m@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 +1,13 @@
+---
+title: Vit Bert Ocr
+emoji: 😻
+colorFrom: purple
+colorTo: purple
+sdk: gradio
+sdk_version: 3.3.1
+app_file: app.py
+pinned: false
+duplicated_from: priyank-m/vit-bert-ocr
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,17 @@
+from transformers import ViTFeatureExtractor, BertTokenizer, VisionEncoderDecoderModel, AutoTokenizer
+import gradio as gr
+
+model=VisionEncoderDecoderModel.from_pretrained("priyank-m/vit-bert-OCR")
+tokenizer =  AutoTokenizer.from_pretrained("bert-base-multilingual-cased")
+feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-large-patch32-384")
+
+def run_ocr(image):
+  pixel_values = feature_extractor(image, return_tensors="pt").pixel_values
+  # autoregressively generate caption (uses greedy decoding by default )
+  generated_ids = model.generate(pixel_values, max_new_tokens=50)
+  generated_text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+  return generated_text
+  
+ 
+demo = gr.Interface(fn=run_ocr, inputs="image", outputs="text")
+demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+transformers
+torch