Map model_type and doc pages names (#14944)

* Map model_type and doc pages names

* Add script

* Fix typo

* Quality

* Manual check for Auto

Co-authored-by: Lysandre <lysandre.debut@reseau.eseo.fr>

utils/check_repo.py

@@ -18,6 +18,7 @@ import inspect
 import os
 import re
 import warnings
+from difflib import get_close_matches
 from pathlib import Path
 
 from transformers import is_flax_available, is_tf_available, is_torch_available
@@ -596,6 +597,33 @@ def check_all_objects_are_documented():
             + "\n - ".join(undocumented_objs)
         )
     check_docstrings_are_in_md()
+    check_model_type_doc_match()
+
+
+def check_model_type_doc_match():
+    """Check all doc pages have a corresponding model type."""
+    model_doc_folder = Path(PATH_TO_DOC) / "model_doc"
+    model_docs = [m.stem for m in model_doc_folder.glob("*.mdx")]
+
+    model_types = list(transformers.models.auto.configuration_auto.MODEL_NAMES_MAPPING.keys())
+
+    errors = []
+    for m in model_docs:
+        if m not in model_types and m != "auto":
+            close_matches = get_close_matches(m, model_types)
+            error_message = f"{m} is not a proper model identifier."
+            if len(close_matches) > 0:
+                close_matches = "/".join(close_matches)
+                error_message += f" Did you mean {close_matches}?"
+            errors.append(error_message)
+
+    if len(errors) > 0:
+        raise ValueError(
+            "Some model doc pages do not match any existing model type:\n"
+            + "\n".join(errors)
+            + "\nYou can add any missing model type to the `MODEL_NAMES_MAPPING` constant in "
+            "models/auto/configuration_auto.py."
+        )
 
 
 # Re pattern to catch :obj:`xx`, :class:`xx`, :func:`xx` or :meth:`xx`.