Add missing entries in mappings (#16857)

* add missing entries in some mappings

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

src/transformers/models/auto/feature_extraction_auto.py

@@ -57,6 +57,10 @@ FEATURE_EXTRACTOR_MAPPING_NAMES = OrderedDict(
         ("regnet", "ConvNextFeatureExtractor"),
         ("poolformer", "PoolFormerFeatureExtractor"),
         ("maskformer", "MaskFormerFeatureExtractor"),
+        ("data2vec-audio", "Wav2Vec2FeatureExtractor"),
+        ("data2vec-vision", "BeitFeatureExtractor"),
+        ("dpt", "DPTFeatureExtractor"),
+        ("glpn", "GLPNFeatureExtractor"),
     ]
 )
 

src/transformers/models/auto/processing_auto.py

@@ -46,6 +46,12 @@ PROCESSOR_MAPPING_NAMES = OrderedDict(
         ("wav2vec2", "Wav2Vec2Processor"),
         ("wav2vec2_with_lm", "Wav2Vec2ProcessorWithLM"),
         ("vision-text-dual-encoder", "VisionTextDualEncoderProcessor"),
+        ("unispeech", "Wav2Vec2Processor"),
+        ("unispeech-sat", "Wav2Vec2Processor"),
+        ("sew", "Wav2Vec2Processor"),
+        ("sew-d", "Wav2Vec2Processor"),
+        ("vilt", "ViltProcessor"),
+        ("wavlm", "Wav2Vec2Processor"),
     ]
 )
 

src/transformers/models/auto/tokenization_auto.py

@@ -241,6 +241,24 @@ else:
                     "XGLMTokenizerFast" if is_tokenizers_available() else None,
                 ),
             ),
+            ("visual_bert", ("BertTokenizer", "BertTokenizerFast" if is_tokenizers_available() else None)),
+            ("megatron-bert", ("BertTokenizer", "BertTokenizerFast" if is_tokenizers_available() else None)),
+            (
+                "nystromformer",
+                (
+                    "AlbertTokenizer" if is_sentencepiece_available() else None,
+                    "AlbertTokenizerFast" if is_tokenizers_available() else None,
+                ),
+            ),
+            ("xlm-roberta-xl", ("RobertaTokenizer", "RobertaTokenizerFast" if is_tokenizers_available() else None)),
+            (
+                "yoso",
+                (
+                    "AlbertTokenizer" if is_sentencepiece_available() else None,
+                    "AlbertTokenizerFast" if is_tokenizers_available() else None,
+                ),
+            ),
+            ("data2vec-text", ("RobertaTokenizer", "RobertaTokenizerFast" if is_tokenizers_available() else None)),
         ]
     )