feat: update Python processors and add utility scripts

- Update ASR, face, OCR, pose processors
- Add release pre-flight check script
- Add synonym generation, chunk processing scripts
- Add face recognition, stamp search utilities

scripts/check_all_stamps.py

@@ -0,0 +1,142 @@
+#!/opt/homebrew/bin/python3.11
+"""
+Find ALL Stamps in the Image using Florence-2
+"""
+
+import os
+import cv2
+from PIL import Image
+from transformers import AutoProcessor, AutoModelForCausalLM
+
+UUID = "384b0ff44aaaa1f1"
+OUTPUT_DIR = f"output/{UUID}/florence2_results"
+INPUT_IMG = os.path.join(OUTPUT_DIR, f"raw_6846.jpg")
+OUTPUT_IMG = os.path.join(OUTPUT_DIR, f"all_stamps_detected.jpg")
+
+# Patch for compatibility (Same as before)
+import types
+
+
+def patch_model(model):
+    inner_model = model.language_model
+    original_prepare = inner_model.prepare_inputs_for_generation
+
+    def patched_prepare(
+        self,
+        input_ids,
+        past_key_values=None,
+        attention_mask=None,
+        inputs_embeds=None,
+        **kwargs,
+    ):
+        is_valid_cache = False
+        if past_key_values is not None:
+            if isinstance(past_key_values, (list, tuple)) and len(past_key_values) > 0:
+                first_layer = past_key_values[0]
+                if first_layer is not None and (
+                    not isinstance(first_layer, (list, tuple)) or len(first_layer) > 0
+                ):
+                    is_valid_cache = True
+
+        if not is_valid_cache:
+            return {
+                "input_ids": input_ids,
+                "attention_mask": attention_mask,
+                "past_key_values": None,
+                "use_cache": True,
+            }
+        else:
+            return original_prepare(
+                input_ids,
+                past_key_values=past_key_values,
+                attention_mask=attention_mask,
+                inputs_embeds=inputs_embeds,
+                **kwargs,
+            )
+
+    inner_model.prepare_inputs_for_generation = types.MethodType(
+        patched_prepare, inner_model
+    )
+
+
+print(f"📷 Loading image from {INPUT_IMG}...")
+if not os.path.exists(INPUT_IMG):
+    print("❌ Image not found.")
+    exit()
+
+image = Image.open(INPUT_IMG).convert("RGB")
+print(f"📐 Image Size: {image.width}x{image.height}")
+
+print("🧠 Loading Florence-2 model...")
+try:
+    processor = AutoProcessor.from_pretrained(
+        "microsoft/Florence-2-base", trust_remote_code=True
+    )
+    model = AutoModelForCausalLM.from_pretrained(
+        "microsoft/Florence-2-base", trust_remote_code=True, attn_implementation="eager"
+    )
+    patch_model(model)
+
+    prompt = "<OPEN_VOCABULARY_DETECTION>"
+    text_input = "stamp"
+
+    print(f"🔍 Scanning for '{text_input}'...")
+    inputs = processor(text=prompt, images=image, return_tensors="pt")
+
+    generated_ids = model.generate(
+        input_ids=inputs["input_ids"],
+        pixel_values=inputs["pixel_values"],
+        max_new_tokens=2048,
+        num_beams=3,
+    )
+
+    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
+
+    # Parse result
+    parsed_answer = processor.post_process_generation(
+        generated_text, task=prompt, image_size=(image.width, image.height)
+    )
+
+    print(f"📦 Raw Parsed Data: {parsed_answer}")
+
+    results = parsed_answer.get("<OPEN_VOCABULARY_DETECTION>", {})
+    bboxes = results.get("bboxes", [])
+    labels = results.get("bboxes_labels", [])
+
+    print(f"✅ Found {len(bboxes)} stamp(s)!")
+
+    # Draw results
+    img_cv = cv2.imread(INPUT_IMG)
+    colors = [
+        (0, 255, 0),
+        (255, 0, 0),
+        (0, 0, 255),
+        (255, 255, 0),
+    ]  # Green, Blue, Red, Yellow
+
+    for i, (box, label) in enumerate(zip(bboxes, labels)):
+        x1, y1, x2, y2 = map(int, box)
+        color = colors[i % len(colors)]
+
+        # Draw box
+        cv2.rectangle(img_cv, (x1, y1), (x2, y2), color, 4)
+
+        # Draw label background
+        text = f"{label} {i + 1}"
+        (tw, th), _ = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 1, 2)
+        cv2.rectangle(img_cv, (x1, y1 - th - 10), (x1 + tw + 10, y1), color, -1)
+
+        # Draw text
+        cv2.putText(
+            img_cv, text, (x1 + 5, y1 - 5), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 0), 2
+        )
+        print(f"   📍 Stamp #{i + 1} at ({x1}, {y1}) -> ({x2}, {y2})")
+
+    cv2.imwrite(OUTPUT_IMG, img_cv)
+    print(f"\n🎨 Image with all detections saved to: {OUTPUT_IMG}")
+
+except Exception as e:
+    print(f"❌ Error: {e}")
+    import traceback
+
+    traceback.print_exc()