Update model card (README.md) via PechaBridge

README.md

@@ -44,21 +44,35 @@ Each image produces a `.txt` transcript and an `*_overlay.jpg` with detected lin
 If you need to call the model directly from Python, you must apply the BDRC-style preprocessing manually before passing pixel values to the model. See `pechabridge/ocr/preprocess_bdrc.py` in the PechaBridge repository for the full preprocessing pipeline (`gray` pipeline was used for this checkpoint).
 
 ```python
-# Minimal example — apply BDRC gray preprocessing first
+# Minimal example — BDRC gray preprocessing applied explicitly
 import torch
 from transformers import VisionEncoderDecoderModel, AutoTokenizer
-from pechabridge.ocr.preprocess_bdrc import BDRCPreprocessConfig, preprocess_line_image_bdrc
+from pechabridge.ocr.preprocess_bdrc import (
+    BDRCPreprocessConfig,
+    preprocess_image_bdrc,       # returns grayscale PIL Image (mode 'L')
+    bdrc_image_to_normalized_tensor,  # grayscale PIL → float32 HW in [-1, 1]
+)
 from PIL import Image
 import numpy as np
 
 model = VisionEncoderDecoderModel.from_pretrained("TibetanCodexAITeam/PechaBridgeOCR")
 tokenizer = AutoTokenizer.from_pretrained("TibetanCodexAITeam/PechaBridgeOCR")
 
-# Load and preprocess a line crop with the BDRC pipeline
+# 1. Load the line crop as RGB
 image = Image.open('line_crop.png').convert('RGB')
-cfg = BDRCPreprocessConfig()  # uses training defaults
-preprocessed = preprocess_line_image_bdrc(np.array(image), cfg)  # returns float32 CHW in [-1, 1]
-pixel_values = torch.tensor(preprocessed).unsqueeze(0)  # add batch dim
+
+# 2. Apply BDRC preprocessing:
+#    - converts to grayscale (luma by default)
+#    - optionally normalises background, binarises, pads/resizes
+#    Returns a grayscale PIL Image (mode 'L')
+cfg = BDRCPreprocessConfig.ocr_line_defaults()  # defaults used during training
+gray_pil = preprocess_image_bdrc(image, cfg)
+
+# 3. Normalise to float32 in [-1, 1] and build a 3-channel tensor
+#    (model expects C=3; replicate the single gray channel)
+gray_hw = bdrc_image_to_normalized_tensor(image, cfg)  # shape: (H, W), float32
+pixel_values = torch.tensor(gray_hw).unsqueeze(0).unsqueeze(0)  # (1, 1, H, W)
+pixel_values = pixel_values.expand(-1, 3, -1, -1)               # (1, 3, H, W)
 
 generated_ids = model.generate(pixel_values)
 text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]