Upload processor_flamingo.py with huggingface_hub

processor_flamingo.py

@@ -1,6 +1,7 @@
 from transformers import ProcessorMixin, AutoProcessor
 from transformers.models.auto.processing_auto import AutoProcessor
 from transformers.processing_utils import ProcessorMixin
+from transformers.tokenization_utils_base import BatchEncoding
 import json
 import os
 
@@ -8,12 +9,12 @@ class FlamingoProcessor(ProcessorMixin):
     """
     Custom processor that combines a tokenizer and feature extractor.
     """
-    attributes = ["feature_extractor", "tokenizer"]
-    feature_extractor_class = "AutoImageProcessor"
+    attributes = ["image_processor", "tokenizer"]
+    image_processor_class = "AutoImageProcessor"
     tokenizer_class = "AutoTokenizer"
     
-    def __init__(self, feature_extractor, tokenizer):
-        super().__init__(feature_extractor, tokenizer)
+    def __init__(self, image_processor, tokenizer):
+        super().__init__(image_processor, tokenizer)
     
     def __call__(self, text=None, images=None, **kwargs):
         """
@@ -22,7 +23,7 @@ class FlamingoProcessor(ProcessorMixin):
         Args:
             text: Text input(s) to tokenize
             images: Image input(s) to process
-            **kwargs: Additional arguments passed to tokenizer/feature_extractor
+            **kwargs: Additional arguments passed to tokenizer/image_processor
         
         Returns:
             Dictionary with processed inputs
@@ -37,18 +38,25 @@ class FlamingoProcessor(ProcessorMixin):
             if type(text) == str:
                 all_text = "<image> " + text
             else:
-                all_text = ["<image> " + _text for _text in text]
+                if type(text[0]) == str:
+                    all_text = ["<image> " + _text for _text in text]
+                else:
+                    all_text = ['<image> ' + " ".join(_text) for _text in text]
             text_encoding = self.tokenizer(all_text, **kwargs)
+
+            import pdb
+            pdb.set_trace()
+
             encoding.update(text_encoding)
         
         # Process images if provided
         if images is not None:
-            image_encoding = self.feature_extractor(images, **kwargs)
+            image_encoding = self.image_processor(images, **kwargs)
             # Add prefix to avoid key conflicts
             for key, value in image_encoding.items():
                 encoding[f"pixel_values" if key == "pixel_values" else f"image_{key}"] = value
         
-        return encoding
+        return BatchEncoding(encoding)
     
     def batch_decode(self, *args, **kwargs):
         """