diff --git a/src/transformers/models/bert/modeling_bert.py b/src/transformers/models/bert/modeling_bert.py
index 65bb8a2ddb7..4537d98497e 100755
--- a/src/transformers/models/bert/modeling_bert.py
+++ b/src/transformers/models/bert/modeling_bert.py
@@ -56,7 +56,6 @@ logger = logging.get_logger(__name__)
 
 _CHECKPOINT_FOR_DOC = "bert-base-uncased"
 _CONFIG_FOR_DOC = "BertConfig"
-_TOKENIZER_FOR_DOC = "BertTokenizer"
 
 # TokenClassification docstring
 _CHECKPOINT_FOR_TOKEN_CLASSIFICATION = "dbmdz/bert-large-cased-finetuned-conll03-english"
@@ -911,7 +910,6 @@ class BertModel(BertPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutputWithPoolingAndCrossAttentions,
         config_class=_CONFIG_FOR_DOC,
@@ -1184,7 +1182,6 @@ class BertLMHeadModel(BertPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=CausalLMOutputWithCrossAttentions,
         config_class=_CONFIG_FOR_DOC,
@@ -1329,7 +1326,6 @@ class BertForMaskedLM(BertPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=MaskedLMOutput,
         config_class=_CONFIG_FOR_DOC,
@@ -1537,7 +1533,6 @@ class BertForSequenceClassification(BertPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION,
         output_type=SequenceClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
@@ -1639,7 +1634,6 @@ class BertForMultipleChoice(BertPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, num_choices, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=MultipleChoiceModelOutput,
         config_class=_CONFIG_FOR_DOC,
@@ -1738,7 +1732,6 @@ class BertForTokenClassification(BertPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_TOKEN_CLASSIFICATION,
         output_type=TokenClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
@@ -1821,7 +1814,6 @@ class BertForQuestionAnswering(BertPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_QA,
         output_type=QuestionAnsweringModelOutput,
         config_class=_CONFIG_FOR_DOC,
diff --git a/src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py b/src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py
index b3d9142a2f1..d94e0614d9f 100755
--- a/src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py
+++ b/src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py
@@ -51,21 +51,8 @@ logger = logging.get_logger(__name__)
 
 _CHECKPOINT_FOR_DOC = "google/bigbird-pegasus-large-arxiv"
 _CONFIG_FOR_DOC = "BigBirdPegasusConfig"
-_TOKENIZER_FOR_DOC = "PegasusTokenizerFast"
-
-# Base model docstring
 _EXPECTED_OUTPUT_SHAPE = [1, 7, 1024]
 
-# SequenceClassification docstring
-_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION = "hf-internal-testing/tiny-random-bigbird_pegasus"
-_SEQ_CLASS_EXPECTED_LOSS = 0.69
-_SEQ_CLASS_EXPECTED_OUTPUT = "'LABEL_1'"
-
-# QuestionAsnwering docstring
-_CHECKPOINT_FOR_QA = "hf-internal-testing/tiny-random-bigbird_pegasus"
-_QA_EXPECTED_LOSS = 3.96
-_QA_EXPECTED_OUTPUT = "''"
-
 
 BIGBIRD_PEGASUS_PRETRAINED_MODEL_ARCHIVE_LIST = [
     "google/bigbird-pegasus-large-arxiv",
@@ -2355,7 +2342,6 @@ class BigBirdPegasusDecoder(BigBirdPegasusPreTrainedModel):
     "The bare BigBirdPegasus Model outputting raw hidden-states without any specific head on top.",
     BIGBIRD_PEGASUS_START_DOCSTRING,
 )
-# Copied from transformers.models.bart.modeling_bart.BartModel with Bart->BigBirdPegasus, BART->BIGBIRD_PEGASUS
 class BigBirdPegasusModel(BigBirdPegasusPreTrainedModel):
     _keys_to_ignore_on_load_missing = ["encoder.embed_tokens.weight", "decoder.embed_tokens.weight"]
 
@@ -2387,12 +2373,12 @@ class BigBirdPegasusModel(BigBirdPegasusPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(BIGBIRD_PEGASUS_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=Seq2SeqModelOutput,
         config_class=_CONFIG_FOR_DOC,
         expected_output=_EXPECTED_OUTPUT_SHAPE,
     )
+    # Copied from transformers.models.bart.modeling_bart.BartModel.forward with Bart->BigBirdPegasus
     def forward(
         self,
         input_ids: torch.LongTensor = None,
@@ -2665,7 +2651,6 @@ class BigBirdPegasusForConditionalGeneration(BigBirdPegasusPreTrainedModel):
     """,
     BIGBIRD_PEGASUS_START_DOCSTRING,
 )
-# Copied from transformers.models.bart.modeling_bart.BartForSequenceClassification with Bart->BigBirdPegasus, BART->BIGBIRD_PEGASUS
 class BigBirdPegasusForSequenceClassification(BigBirdPegasusPreTrainedModel):
     _keys_to_ignore_on_load_missing = ["encoder.embed_tokens.weight", "decoder.embed_tokens.weight"]
 
@@ -2683,13 +2668,11 @@ class BigBirdPegasusForSequenceClassification(BigBirdPegasusPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(BIGBIRD_PEGASUS_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION,
+        checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=Seq2SeqSequenceClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
-        expected_output=_SEQ_CLASS_EXPECTED_OUTPUT,
-        expected_loss=_SEQ_CLASS_EXPECTED_LOSS,
     )
+    # Copied from transformers.models.bart.modeling_bart.BartForSequenceClassification.forward
     def forward(
         self,
         input_ids: torch.LongTensor = None,
@@ -2795,7 +2778,6 @@ class BigBirdPegasusForSequenceClassification(BigBirdPegasusPreTrainedModel):
     """,
     BIGBIRD_PEGASUS_START_DOCSTRING,
 )
-# Copied from transformers.models.bart.modeling_bart.BartForQuestionAnswering with Bart->BigBirdPegasus, BART->BIGBIRD_PEGASUS
 class BigBirdPegasusForQuestionAnswering(BigBirdPegasusPreTrainedModel):
     _keys_to_ignore_on_load_missing = ["encoder.embed_tokens.weight", "decoder.embed_tokens.weight"]
 
@@ -2812,13 +2794,11 @@ class BigBirdPegasusForQuestionAnswering(BigBirdPegasusPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(BIGBIRD_PEGASUS_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_QA,
+        checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=Seq2SeqQuestionAnsweringModelOutput,
         config_class=_CONFIG_FOR_DOC,
-        expected_loss=_QA_EXPECTED_LOSS,
-        expected_output=_QA_EXPECTED_OUTPUT,
     )
+    # Copied from transformers.models.bart.modeling_bart.BartForQuestionAnswering.forward
     def forward(
         self,
         input_ids: torch.Tensor = None,
diff --git a/src/transformers/models/data2vec/modeling_data2vec_audio.py b/src/transformers/models/data2vec/modeling_data2vec_audio.py
index eb40a73ca43..965d250faca 100755
--- a/src/transformers/models/data2vec/modeling_data2vec_audio.py
+++ b/src/transformers/models/data2vec/modeling_data2vec_audio.py
@@ -47,7 +47,6 @@ _HIDDEN_STATES_START_POSITION = 2
 
 # General docstring
 _CONFIG_FOR_DOC = "Data2VecAudioConfig"
-_PROCESSOR_FOR_DOC = "Wav2Vec2Processor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "facebook/data2vec-audio-base-960h"
@@ -57,20 +56,6 @@ _EXPECTED_OUTPUT_SHAPE = [1, 292, 768]
 _CTC_EXPECTED_OUTPUT = "'MISTER QUILTER IS THE APOSTLE OF THE MIDDLE CLASSES AND WE ARE GLAD TO WELCOME HIS GOSPEL'"
 _CTC_EXPECTED_LOSS = 66.95
 
-# Audio class docstring
-_FEAT_EXTRACTOR_FOR_DOC = "Wav2Vec2FeatureExtractor"
-_SEQ_CLASS_CHECKPOINT = "hf-internal-testing/tiny-random-data2vec-seq-class"
-_SEQ_CLASS_EXPECTED_OUTPUT = "'LABEL_1'"
-_SEQ_CLASS_EXPECTED_LOSS = 0.69
-
-# Frame class docstring
-_FRAME_CLASS_CHECKPOINT = "hf-internal-testing/tiny-random-data2vec-audio-frame"
-_FRAME_EXPECTED_OUTPUT = [1, 1]
-
-# Speaker Verification docstring
-_XVECTOR_CHECKPOINT = "hf-internal-testing/tiny-random-data2vec-xvector"
-_XVECTOR_EXPECTED_OUTPUT = 1.0
-
 
 DATA2VEC_AUDIO_PRETRAINED_MODEL_ARCHIVE_LIST = [
     "facebook/data2vec-audio-base",
@@ -917,12 +902,12 @@ class Data2VecAudioModel(Data2VecAudioPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DATA2VEC_AUDIO_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_PROCESSOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=Wav2Vec2BaseModelOutput,
         config_class=_CONFIG_FOR_DOC,
         modality="audio",
         expected_output=_EXPECTED_OUTPUT_SHAPE,
+        processor_class="AutoProcessor",
     )
     def forward(
         self,
@@ -981,7 +966,6 @@ class Data2VecAudioModel(Data2VecAudioPreTrainedModel):
     """Data2VecAudio Model with a `language modeling` head on top for Connectionist Temporal Classification (CTC).""",
     DATA2VEC_AUDIO_START_DOCSTRING,
 )
-# Copied from transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForCTC with Wav2Vec2->Data2VecAudio, wav2vec2->data2vec_audio, WAV_2_VEC_2->DATA2VEC_AUDIO
 class Data2VecAudioForCTC(Data2VecAudioPreTrainedModel):
     def __init__(self, config):
         super().__init__(config)
@@ -1025,13 +1009,13 @@ class Data2VecAudioForCTC(Data2VecAudioPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DATA2VEC_AUDIO_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_PROCESSOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=CausalLMOutput,
         config_class=_CONFIG_FOR_DOC,
         expected_output=_CTC_EXPECTED_OUTPUT,
         expected_loss=_CTC_EXPECTED_LOSS,
     )
+    # Copied from transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForCTC.forward with wav2vec2->data2vec_audio
     def forward(
         self,
         input_values: Optional[torch.Tensor],
@@ -1112,7 +1096,6 @@ class Data2VecAudioForCTC(Data2VecAudioPreTrainedModel):
     """,
     DATA2VEC_AUDIO_START_DOCSTRING,
 )
-# Copied from transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForSequenceClassification with Wav2Vec2->Data2VecAudio, wav2vec2->data2vec_audio, WAV_2_VEC_2->DATA2VEC_AUDIO
 class Data2VecAudioForSequenceClassification(Data2VecAudioPreTrainedModel):
     def __init__(self, config):
         super().__init__(config)
@@ -1160,14 +1143,12 @@ class Data2VecAudioForSequenceClassification(Data2VecAudioPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DATA2VEC_AUDIO_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
-        checkpoint=_SEQ_CLASS_CHECKPOINT,
+        checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=SequenceClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
         modality="audio",
-        expected_output=_SEQ_CLASS_EXPECTED_OUTPUT,
-        expected_loss=_SEQ_CLASS_EXPECTED_LOSS,
     )
+    # Copied from transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForSequenceClassification.forward with wav2vec2->data2vec_audio
     def forward(
         self,
         input_values: Optional[torch.Tensor],
@@ -1236,7 +1217,6 @@ class Data2VecAudioForSequenceClassification(Data2VecAudioPreTrainedModel):
     """,
     DATA2VEC_AUDIO_START_DOCSTRING,
 )
-# Copied from transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForAudioFrameClassification with Wav2Vec2->Data2VecAudio, wav2vec2->data2vec_audio, WAV_2_VEC_2->DATA2VEC_AUDIO
 class Data2VecAudioForAudioFrameClassification(Data2VecAudioPreTrainedModel):
     def __init__(self, config):
         super().__init__(config)
@@ -1284,13 +1264,12 @@ class Data2VecAudioForAudioFrameClassification(Data2VecAudioPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DATA2VEC_AUDIO_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
-        checkpoint=_FRAME_CLASS_CHECKPOINT,
+        checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=TokenClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
         modality="audio",
-        expected_output=_FRAME_EXPECTED_OUTPUT,
     )
+    # Copied from transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForAudioFrameClassification.forward with wav2vec2->data2vec_audio
     def forward(
         self,
         input_values: Optional[torch.Tensor],
@@ -1402,7 +1381,6 @@ class TDNNLayer(nn.Module):
     """,
     DATA2VEC_AUDIO_START_DOCSTRING,
 )
-# Copied from transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForXVector with Wav2Vec2->Data2VecAudio, wav2vec2->data2vec_audio, WAV_2_VEC_2->DATA2VEC_AUDIO
 class Data2VecAudioForXVector(Data2VecAudioPreTrainedModel):
     def __init__(self, config):
         super().__init__(config)
@@ -1467,13 +1445,12 @@ class Data2VecAudioForXVector(Data2VecAudioPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DATA2VEC_AUDIO_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
-        checkpoint=_XVECTOR_CHECKPOINT,
+        checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=XVectorOutput,
         config_class=_CONFIG_FOR_DOC,
         modality="audio",
-        expected_output=_XVECTOR_EXPECTED_OUTPUT,
     )
+    # Copied from transformers.models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForXVector.forward with wav2vec2->data2vec_audio
     def forward(
         self,
         input_values: Optional[torch.Tensor],
diff --git a/src/transformers/models/deberta/modeling_deberta.py b/src/transformers/models/deberta/modeling_deberta.py
index ea575a42dad..7dd2b0767c8 100644
--- a/src/transformers/models/deberta/modeling_deberta.py
+++ b/src/transformers/models/deberta/modeling_deberta.py
@@ -38,7 +38,6 @@ from .configuration_deberta import DebertaConfig
 
 logger = logging.get_logger(__name__)
 _CONFIG_FOR_DOC = "DebertaConfig"
-_TOKENIZER_FOR_DOC = "DebertaTokenizer"
 _CHECKPOINT_FOR_DOC = "microsoft/deberta-base"
 
 # Masked LM docstring
@@ -46,14 +45,6 @@ _CHECKPOINT_FOR_MASKED_LM = "lsanochkin/deberta-large-feedback"
 _MASKED_LM_EXPECTED_OUTPUT = "' Paris'"
 _MASKED_LM_EXPECTED_LOSS = "0.54"
 
-# TokenClassification docstring
-_CHECKPOINT_FOR_TOKEN_CLASSIFICATION = "dbsamu/deberta-base-finetuned-ner"
-_TOKEN_CLASS_EXPECTED_OUTPUT = (
-    "['LABEL_0', 'LABEL_0', 'LABEL_0', 'LABEL_0', 'LABEL_0', 'LABEL_0', 'LABEL_0', 'LABEL_0', 'LABEL_0', 'LABEL_0',"
-    " 'LABEL_0', 'LABEL_0']"
-)
-_TOKEN_CLASS_EXPECTED_LOSS = 0.04
-
 # QuestionAnswering docstring
 _CHECKPOINT_FOR_QA = "Palak/microsoft_deberta-large_squad"
 _QA_EXPECTED_OUTPUT = "' a nice puppet'"
@@ -61,11 +52,6 @@ _QA_EXPECTED_LOSS = 0.14
 _QA_TARGET_START_INDEX = 12
 _QA_TARGET_END_INDEX = 14
 
-# SequenceClassification docstring
-_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION = "hf-internal-testing/tiny-random-deberta"
-_SEQ_CLASS_EXPECTED_OUTPUT = "'LABEL_0'"
-_SEQ_CLASS_EXPECTED_LOSS = "0.69"
-
 
 DEBERTA_PRETRAINED_MODEL_ARCHIVE_LIST = [
     "microsoft/deberta-base",
@@ -950,7 +936,6 @@ class DebertaModel(DebertaPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DEBERTA_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutput,
         config_class=_CONFIG_FOR_DOC,
@@ -1057,7 +1042,6 @@ class DebertaForMaskedLM(DebertaPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DEBERTA_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_MASKED_LM,
         output_type=MaskedLMOutput,
         config_class=_CONFIG_FOR_DOC,
@@ -1201,12 +1185,9 @@ class DebertaForSequenceClassification(DebertaPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DEBERTA_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION,
+        checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=SequenceClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
-        expected_output=_SEQ_CLASS_EXPECTED_OUTPUT,
-        expected_loss=_SEQ_CLASS_EXPECTED_LOSS,
     )
     def forward(
         self,
@@ -1311,12 +1292,9 @@ class DebertaForTokenClassification(DebertaPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DEBERTA_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_TOKEN_CLASSIFICATION,
+        checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=TokenClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
-        expected_output=_TOKEN_CLASS_EXPECTED_OUTPUT,
-        expected_loss=_TOKEN_CLASS_EXPECTED_LOSS,
     )
     def forward(
         self,
@@ -1388,7 +1366,6 @@ class DebertaForQuestionAnswering(DebertaPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DEBERTA_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_QA,
         output_type=QuestionAnsweringModelOutput,
         config_class=_CONFIG_FOR_DOC,
diff --git a/src/transformers/models/deberta_v2/modeling_deberta_v2.py b/src/transformers/models/deberta_v2/modeling_deberta_v2.py
index 1231aec46e7..bc38defb864 100644
--- a/src/transformers/models/deberta_v2/modeling_deberta_v2.py
+++ b/src/transformers/models/deberta_v2/modeling_deberta_v2.py
@@ -40,34 +40,10 @@ from .configuration_deberta_v2 import DebertaV2Config
 logger = logging.get_logger(__name__)
 
 _CONFIG_FOR_DOC = "DebertaV2Config"
-_TOKENIZER_FOR_DOC = "DebertaV2Tokenizer"
 _CHECKPOINT_FOR_DOC = "microsoft/deberta-v2-xlarge"
-
-# Masked LM docstring
-_CHECKPOINT_FOR_MASKED_LM = "hf-internal-testing/tiny-random-deberta-v2"
-_MASKED_LM_EXPECTED_OUTPUT = "'enberry'"
-_MASKED_LM_EXPECTED_LOSS = "11.85"
-
-# TokenClassification docstring
-_CHECKPOINT_FOR_TOKEN_CLASSIFICATION = "hf-internal-testing/tiny-random-deberta-v2"
-_TOKEN_CLASS_EXPECTED_OUTPUT = (
-    "['LABEL_0', 'LABEL_0', 'LABEL_1', 'LABEL_0', 'LABEL_0', 'LABEL_1', 'LABEL_0', 'LABEL_0', 'LABEL_0', 'LABEL_0',"
-    " 'LABEL_0', 'LABEL_0']"
-)
-_TOKEN_CLASS_EXPECTED_LOSS = 0.61
-
-# QuestionAnswering docstring
-_CHECKPOINT_FOR_QA = "hf-internal-testing/tiny-random-deberta-v2"
-_QA_EXPECTED_OUTPUT = "'was Jim Henson? Jim Henson was'"
-_QA_EXPECTED_LOSS = 2.47
 _QA_TARGET_START_INDEX = 2
 _QA_TARGET_END_INDEX = 9
 
-# SequenceClassification docstring
-_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION = "hf-internal-testing/tiny-random-deberta-v2"
-_SEQ_CLASS_EXPECTED_OUTPUT = "'LABEL_1'"
-_SEQ_CLASS_EXPECTED_LOSS = "0.69"
-
 DEBERTA_V2_PRETRAINED_MODEL_ARCHIVE_LIST = [
     "microsoft/deberta-v2-xlarge",
     "microsoft/deberta-v2-xxlarge",
@@ -1060,7 +1036,6 @@ class DebertaV2Model(DebertaV2PreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DEBERTA_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutput,
         config_class=_CONFIG_FOR_DOC,
@@ -1146,7 +1121,6 @@ class DebertaV2Model(DebertaV2PreTrainedModel):
 
 
 @add_start_docstrings("""DeBERTa Model with a `language modeling` head on top.""", DEBERTA_START_DOCSTRING)
-# Copied from transformers.models.deberta.modeling_deberta.DebertaForMaskedLM with Deberta->DebertaV2
 class DebertaV2ForMaskedLM(DebertaV2PreTrainedModel):
     _keys_to_ignore_on_load_unexpected = [r"pooler"]
     _keys_to_ignore_on_load_missing = [r"position_ids", r"predictions.decoder.bias", "cls.predictions.decoder.weight"]
@@ -1168,14 +1142,12 @@ class DebertaV2ForMaskedLM(DebertaV2PreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DEBERTA_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_MASKED_LM,
+        checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=MaskedLMOutput,
         config_class=_CONFIG_FOR_DOC,
         mask="[MASK]",
-        expected_output=_MASKED_LM_EXPECTED_OUTPUT,
-        expected_loss=_MASKED_LM_EXPECTED_LOSS,
     )
+    # Copied from transformers.models.deberta.modeling_deberta.DebertaForMaskedLM.forward with Deberta->DebertaV2
     def forward(
         self,
         input_ids: Optional[torch.Tensor] = None,
@@ -1285,7 +1257,6 @@ class DebertaV2OnlyMLMHead(nn.Module):
     """,
     DEBERTA_START_DOCSTRING,
 )
-# Copied from transformers.models.deberta.modeling_deberta.DebertaForSequenceClassification with Deberta->DebertaV2
 class DebertaV2ForSequenceClassification(DebertaV2PreTrainedModel):
     def __init__(self, config):
         super().__init__(config)
@@ -1313,13 +1284,11 @@ class DebertaV2ForSequenceClassification(DebertaV2PreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DEBERTA_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION,
+        checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=SequenceClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
-        expected_output=_SEQ_CLASS_EXPECTED_OUTPUT,
-        expected_loss=_SEQ_CLASS_EXPECTED_LOSS,
     )
+    # Copied from transformers.models.deberta.modeling_deberta.DebertaForSequenceClassification.forward with Deberta->DebertaV2
     def forward(
         self,
         input_ids: Optional[torch.Tensor] = None,
@@ -1424,12 +1393,9 @@ class DebertaV2ForTokenClassification(DebertaV2PreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DEBERTA_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_TOKEN_CLASSIFICATION,
+        checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=TokenClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
-        expected_output=_TOKEN_CLASS_EXPECTED_OUTPUT,
-        expected_loss=_TOKEN_CLASS_EXPECTED_LOSS,
     )
     def forward(
         self,
@@ -1486,7 +1452,6 @@ class DebertaV2ForTokenClassification(DebertaV2PreTrainedModel):
     """,
     DEBERTA_START_DOCSTRING,
 )
-# Copied from transformers.models.deberta.modeling_deberta.DebertaForQuestionAnswering with Deberta->DebertaV2
 class DebertaV2ForQuestionAnswering(DebertaV2PreTrainedModel):
     _keys_to_ignore_on_load_unexpected = [r"pooler"]
 
@@ -1502,15 +1467,13 @@ class DebertaV2ForQuestionAnswering(DebertaV2PreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DEBERTA_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_QA,
+        checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=QuestionAnsweringModelOutput,
         config_class=_CONFIG_FOR_DOC,
-        expected_output=_QA_EXPECTED_OUTPUT,
-        expected_loss=_QA_EXPECTED_LOSS,
         qa_target_start_index=_QA_TARGET_START_INDEX,
         qa_target_end_index=_QA_TARGET_END_INDEX,
     )
+    # Copied from transformers.models.deberta.modeling_deberta.DebertaForQuestionAnswering.forward with Deberta->DebertaV2
     def forward(
         self,
         input_ids: Optional[torch.Tensor] = None,
@@ -1617,7 +1580,6 @@ class DebertaV2ForMultipleChoice(DebertaV2PreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DEBERTA_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=MultipleChoiceModelOutput,
         config_class=_CONFIG_FOR_DOC,
diff --git a/src/transformers/models/mobilebert/modeling_mobilebert.py b/src/transformers/models/mobilebert/modeling_mobilebert.py
index 8b04dce1882..99d68eec3f4 100644
--- a/src/transformers/models/mobilebert/modeling_mobilebert.py
+++ b/src/transformers/models/mobilebert/modeling_mobilebert.py
@@ -58,7 +58,6 @@ logger = logging.get_logger(__name__)
 
 _CHECKPOINT_FOR_DOC = "google/mobilebert-uncased"
 _CONFIG_FOR_DOC = "MobileBertConfig"
-_TOKENIZER_FOR_DOC = "MobileBertTokenizer"
 
 # TokenClassification docstring
 _CHECKPOINT_FOR_TOKEN_CLASSIFICATION = "mrm8488/mobilebert-finetuned-ner"
@@ -842,7 +841,6 @@ class MobileBertModel(MobileBertPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(MOBILEBERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutputWithPooling,
         config_class=_CONFIG_FOR_DOC,
@@ -1069,7 +1067,6 @@ class MobileBertForMaskedLM(MobileBertPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(MOBILEBERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=MaskedLMOutput,
         config_class=_CONFIG_FOR_DOC,
@@ -1265,7 +1262,6 @@ class MobileBertForSequenceClassification(MobileBertPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(MOBILEBERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION,
         output_type=SequenceClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
@@ -1368,7 +1364,6 @@ class MobileBertForQuestionAnswering(MobileBertPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(MOBILEBERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_QA,
         output_type=QuestionAnsweringModelOutput,
         config_class=_CONFIG_FOR_DOC,
@@ -1478,7 +1473,6 @@ class MobileBertForMultipleChoice(MobileBertPreTrainedModel):
         MOBILEBERT_INPUTS_DOCSTRING.format("batch_size, num_choices, sequence_length")
     )
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=MultipleChoiceModelOutput,
         config_class=_CONFIG_FOR_DOC,
@@ -1578,7 +1572,6 @@ class MobileBertForTokenClassification(MobileBertPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(MOBILEBERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_TOKENIZER_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_TOKEN_CLASSIFICATION,
         output_type=TokenClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
diff --git a/src/transformers/utils/doc.py b/src/transformers/utils/doc.py
index 0e68b5d7f23..626c6816b25 100644
--- a/src/transformers/utils/doc.py
+++ b/src/transformers/utils/doc.py
@@ -150,10 +150,10 @@ PT_TOKEN_CLASSIFICATION_SAMPLE = r"""
     Example:
 
     ```python
-    >>> from transformers import {processor_class}, {model_class}
+    >>> from transformers import AutoTokenizer, {model_class}
     >>> import torch
 
-    >>> tokenizer = {processor_class}.from_pretrained("{checkpoint}")
+    >>> tokenizer = AutoTokenizer.from_pretrained("{checkpoint}")
     >>> model = {model_class}.from_pretrained("{checkpoint}")
 
     >>> inputs = tokenizer(
@@ -171,9 +171,7 @@ PT_TOKEN_CLASSIFICATION_SAMPLE = r"""
     >>> predicted_tokens_classes = [model.config.id2label[t.item()] for t in predicted_token_class_ids[0]]
     >>> predicted_tokens_classes
     {expected_output}
-    ```
 
-    ```python
     >>> labels = predicted_token_class_ids
     >>> loss = model(**inputs, labels=labels).loss
     >>> round(loss.item(), 2)
@@ -185,10 +183,10 @@ PT_QUESTION_ANSWERING_SAMPLE = r"""
     Example:
 
     ```python
-    >>> from transformers import {processor_class}, {model_class}
+    >>> from transformers import AutoTokenizer, {model_class}
     >>> import torch
 
-    >>> tokenizer = {processor_class}.from_pretrained("{checkpoint}")
+    >>> tokenizer = AutoTokenizer.from_pretrained("{checkpoint}")
     >>> model = {model_class}.from_pretrained("{checkpoint}")
 
     >>> question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
@@ -203,9 +201,7 @@ PT_QUESTION_ANSWERING_SAMPLE = r"""
     >>> predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]
     >>> tokenizer.decode(predict_answer_tokens, skip_special_tokens=True)
     {expected_output}
-    ```
 
-    ```python
     >>> # target is "nice puppet"
     >>> target_start_index = torch.tensor([{qa_target_start_index}])
     >>> target_end_index = torch.tensor([{qa_target_end_index}])
@@ -222,9 +218,9 @@ PT_SEQUENCE_CLASSIFICATION_SAMPLE = r"""
 
     ```python
     >>> import torch
-    >>> from transformers import {processor_class}, {model_class}
+    >>> from transformers import AutoTokenizer, {model_class}
 
-    >>> tokenizer = {processor_class}.from_pretrained("{checkpoint}")
+    >>> tokenizer = AutoTokenizer.from_pretrained("{checkpoint}")
     >>> model = {model_class}.from_pretrained("{checkpoint}")
 
     >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
@@ -235,9 +231,7 @@ PT_SEQUENCE_CLASSIFICATION_SAMPLE = r"""
     >>> predicted_class_id = logits.argmax().item()
     >>> model.config.id2label[predicted_class_id]
     {expected_output}
-    ```
 
-    ```python
     >>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
     >>> num_labels = len(model.config.id2label)
     >>> model = {model_class}.from_pretrained("{checkpoint}", num_labels=num_labels)
@@ -252,9 +246,9 @@ PT_SEQUENCE_CLASSIFICATION_SAMPLE = r"""
 
     ```python
     >>> import torch
-    >>> from transformers import {processor_class}, {model_class}
+    >>> from transformers import AutoTokenizer, {model_class}
 
-    >>> tokenizer = {processor_class}.from_pretrained("{checkpoint}")
+    >>> tokenizer = AutoTokenizer.from_pretrained("{checkpoint}")
     >>> model = {model_class}.from_pretrained("{checkpoint}", problem_type="multi_label_classification")
 
     >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
@@ -262,23 +256,16 @@ PT_SEQUENCE_CLASSIFICATION_SAMPLE = r"""
     >>> with torch.no_grad():
     ...     logits = model(**inputs).logits
 
-    >>> predicted_class_id = logits.argmax().item()
-    >>> model.config.id2label[predicted_class_id]
-    {expected_output}
-    ```
+    >>> predicted_class_ids = torch.arange(0, logits.shape[-1])[torch.sigmoid(logits).squeeze() > 0.5]
 
-    ```python
     >>> # To train a model on `num_labels` classes, you can pass `num_labels=num_labels` to `.from_pretrained(...)`
     >>> num_labels = len(model.config.id2label)
     >>> model = {model_class}.from_pretrained(
     ...     "{checkpoint}", num_labels=num_labels, problem_type="multi_label_classification"
     ... )
 
-    >>> labels = torch.nn.functional.one_hot(torch.tensor([predicted_class_id]), num_classes=num_labels).to(
-    ...     torch.float
-    ... )
+    >>> labels = torch.nn.functional.one_hot(torch.tensor(predicted_class_ids), num_classes=num_labels).to(torch.float)
     >>> loss = model(**inputs, labels=labels).loss
-    >>> loss.backward()  # doctest: +IGNORE_RESULT
     ```
 """
 
@@ -286,10 +273,10 @@ PT_MASKED_LM_SAMPLE = r"""
     Example:
 
     ```python
-    >>> from transformers import {processor_class}, {model_class}
+    >>> from transformers import AutoTokenizer, {model_class}
     >>> import torch
 
-    >>> tokenizer = {processor_class}.from_pretrained("{checkpoint}")
+    >>> tokenizer = AutoTokenizer.from_pretrained("{checkpoint}")
     >>> model = {model_class}.from_pretrained("{checkpoint}")
 
     >>> inputs = tokenizer("The capital of France is {mask}.", return_tensors="pt")
@@ -303,9 +290,7 @@ PT_MASKED_LM_SAMPLE = r"""
     >>> predicted_token_id = logits[0, mask_token_index].argmax(axis=-1)
     >>> tokenizer.decode(predicted_token_id)
     {expected_output}
-    ```
 
-    ```python
     >>> labels = tokenizer("The capital of France is Paris.", return_tensors="pt")["input_ids"]
     >>> # mask labels of non-{mask} tokens
     >>> labels = torch.where(inputs.input_ids == tokenizer.mask_token_id, labels, -100)
@@ -320,10 +305,10 @@ PT_BASE_MODEL_SAMPLE = r"""
     Example:
 
     ```python
-    >>> from transformers import {processor_class}, {model_class}
+    >>> from transformers import AutoTokenizer, {model_class}
     >>> import torch
 
-    >>> tokenizer = {processor_class}.from_pretrained("{checkpoint}")
+    >>> tokenizer = AutoTokenizer.from_pretrained("{checkpoint}")
     >>> model = {model_class}.from_pretrained("{checkpoint}")
 
     >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
@@ -337,10 +322,10 @@ PT_MULTIPLE_CHOICE_SAMPLE = r"""
     Example:
 
     ```python
-    >>> from transformers import {processor_class}, {model_class}
+    >>> from transformers import AutoTokenizer, {model_class}
     >>> import torch
 
-    >>> tokenizer = {processor_class}.from_pretrained("{checkpoint}")
+    >>> tokenizer = AutoTokenizer.from_pretrained("{checkpoint}")
     >>> model = {model_class}.from_pretrained("{checkpoint}")
 
     >>> prompt = "In Italy, pizza served in formal settings, such as at a restaurant, is presented unsliced."
@@ -362,9 +347,9 @@ PT_CAUSAL_LM_SAMPLE = r"""
 
     ```python
     >>> import torch
-    >>> from transformers import {processor_class}, {model_class}
+    >>> from transformers import AutoTokenizer, {model_class}
 
-    >>> tokenizer = {processor_class}.from_pretrained("{checkpoint}")
+    >>> tokenizer = AutoTokenizer.from_pretrained("{checkpoint}")
     >>> model = {model_class}.from_pretrained("{checkpoint}")
 
     >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
@@ -378,7 +363,7 @@ PT_SPEECH_BASE_MODEL_SAMPLE = r"""
     Example:
 
     ```python
-    >>> from transformers import {processor_class}, {model_class}
+    >>> from transformers import AutoProcessor, {model_class}
     >>> import torch
     >>> from datasets import load_dataset
 
@@ -386,7 +371,7 @@ PT_SPEECH_BASE_MODEL_SAMPLE = r"""
     >>> dataset = dataset.sort("id")
     >>> sampling_rate = dataset.features["audio"].sampling_rate
 
-    >>> processor = {processor_class}.from_pretrained("{checkpoint}")
+    >>> processor = AutoProcessor.from_pretrained("{checkpoint}")
     >>> model = {model_class}.from_pretrained("{checkpoint}")
 
     >>> # audio file is decoded on the fly
@@ -404,7 +389,7 @@ PT_SPEECH_CTC_SAMPLE = r"""
     Example:
 
     ```python
-    >>> from transformers import {processor_class}, {model_class}
+    >>> from transformers import AutoProcessor, {model_class}
     >>> from datasets import load_dataset
     >>> import torch
 
@@ -412,7 +397,7 @@ PT_SPEECH_CTC_SAMPLE = r"""
     >>> dataset = dataset.sort("id")
     >>> sampling_rate = dataset.features["audio"].sampling_rate
 
-    >>> processor = {processor_class}.from_pretrained("{checkpoint}")
+    >>> processor = AutoProcessor.from_pretrained("{checkpoint}")
     >>> model = {model_class}.from_pretrained("{checkpoint}")
 
     >>> # audio file is decoded on the fly
@@ -425,9 +410,7 @@ PT_SPEECH_CTC_SAMPLE = r"""
     >>> transcription = processor.batch_decode(predicted_ids)
     >>> transcription[0]
     {expected_output}
-    ```
 
-    ```python
     >>> inputs["labels"] = processor(text=dataset[0]["text"], return_tensors="pt").input_ids
 
     >>> # compute loss
@@ -441,7 +424,7 @@ PT_SPEECH_SEQ_CLASS_SAMPLE = r"""
     Example:
 
     ```python
-    >>> from transformers import {processor_class}, {model_class}
+    >>> from transformers import AutoFeatureExtractor, {model_class}
     >>> from datasets import load_dataset
     >>> import torch
 
@@ -449,7 +432,7 @@ PT_SPEECH_SEQ_CLASS_SAMPLE = r"""
     >>> dataset = dataset.sort("id")
     >>> sampling_rate = dataset.features["audio"].sampling_rate
 
-    >>> feature_extractor = {processor_class}.from_pretrained("{checkpoint}")
+    >>> feature_extractor = AutoFeatureExtractor.from_pretrained("{checkpoint}")
     >>> model = {model_class}.from_pretrained("{checkpoint}")
 
     >>> # audio file is decoded on the fly
@@ -462,9 +445,7 @@ PT_SPEECH_SEQ_CLASS_SAMPLE = r"""
     >>> predicted_label = model.config.id2label[predicted_class_ids]
     >>> predicted_label
     {expected_output}
-    ```
 
-    ```python
     >>> # compute loss - target_label is e.g. "down"
     >>> target_label = model.config.id2label[0]
     >>> inputs["labels"] = torch.tensor([model.config.label2id[target_label]])
@@ -479,7 +460,7 @@ PT_SPEECH_FRAME_CLASS_SAMPLE = r"""
     Example:
 
     ```python
-    >>> from transformers import {processor_class}, {model_class}
+    >>> from transformers import AutoFeatureExtractor, {model_class}
     >>> from datasets import load_dataset
     >>> import torch
 
@@ -487,7 +468,7 @@ PT_SPEECH_FRAME_CLASS_SAMPLE = r"""
     >>> dataset = dataset.sort("id")
     >>> sampling_rate = dataset.features["audio"].sampling_rate
 
-    >>> feature_extractor = {processor_class}.from_pretrained("{checkpoint}")
+    >>> feature_extractor = AutoFeatureExtractor.from_pretrained("{checkpoint}")
     >>> model = {model_class}.from_pretrained("{checkpoint}")
 
     >>> # audio file is decoded on the fly
@@ -508,7 +489,7 @@ PT_SPEECH_XVECTOR_SAMPLE = r"""
     Example:
 
     ```python
-    >>> from transformers import {processor_class}, {model_class}
+    >>> from transformers import AutoFeatureExtractor, {model_class}
     >>> from datasets import load_dataset
     >>> import torch
 
@@ -516,7 +497,7 @@ PT_SPEECH_XVECTOR_SAMPLE = r"""
     >>> dataset = dataset.sort("id")
     >>> sampling_rate = dataset.features["audio"].sampling_rate
 
-    >>> feature_extractor = {processor_class}.from_pretrained("{checkpoint}")
+    >>> feature_extractor = AutoFeatureExtractor.from_pretrained("{checkpoint}")
     >>> model = {model_class}.from_pretrained("{checkpoint}")
 
     >>> # audio file is decoded on the fly
@@ -543,17 +524,17 @@ PT_VISION_BASE_MODEL_SAMPLE = r"""
     Example:
 
     ```python
-    >>> from transformers import {processor_class}, {model_class}
+    >>> from transformers import AutoImageProcessor, {model_class}
     >>> import torch
     >>> from datasets import load_dataset
 
     >>> dataset = load_dataset("huggingface/cats-image")
     >>> image = dataset["test"]["image"][0]
 
-    >>> feature_extractor = {processor_class}.from_pretrained("{checkpoint}")
+    >>> image_processor = AutoImageProcessor.from_pretrained("{checkpoint}")
     >>> model = {model_class}.from_pretrained("{checkpoint}")
 
-    >>> inputs = feature_extractor(image, return_tensors="pt")
+    >>> inputs = image_processor(image, return_tensors="pt")
 
     >>> with torch.no_grad():
     ...     outputs = model(**inputs)
@@ -568,17 +549,17 @@ PT_VISION_SEQ_CLASS_SAMPLE = r"""
     Example:
 
     ```python
-    >>> from transformers import {processor_class}, {model_class}
+    >>> from transformers import AutoImageProcessor, {model_class}
     >>> import torch
     >>> from datasets import load_dataset
 
     >>> dataset = load_dataset("huggingface/cats-image")
     >>> image = dataset["test"]["image"][0]
 
-    >>> feature_extractor = {processor_class}.from_pretrained("{checkpoint}")
+    >>> image_processor = AutoImageProcessor.from_pretrained("{checkpoint}")
     >>> model = {model_class}.from_pretrained("{checkpoint}")
 
-    >>> inputs = feature_extractor(image, return_tensors="pt")
+    >>> inputs = image_processor(image, return_tensors="pt")
 
     >>> with torch.no_grad():
     ...     logits = model(**inputs).logits
@@ -1048,6 +1029,20 @@ FLAX_SAMPLE_DOCSTRINGS = {
 }
 
 
+def filter_outputs_from_example(docstring, **kwargs):
+    """
+    Removes the lines testing an output with the doctest syntax in a code sample when it's set to `None`.
+    """
+    for key, value in kwargs.items():
+        if value is not None:
+            continue
+
+        doc_key = "{" + key + "}"
+        docstring = re.sub(rf"\n([^\n]+)\n\s+{doc_key}\n", "\n", docstring)
+
+    return docstring
+
+
 def add_code_sample_docstrings(
     *docstr,
     processor_class=None,
@@ -1059,8 +1054,8 @@ def add_code_sample_docstrings(
     qa_target_end_index=15,
     model_cls=None,
     modality=None,
-    expected_output="",
-    expected_loss="",
+    expected_output=None,
+    expected_loss=None,
 ):
     def docstring_decorator(fn):
         # model_class defaults to function's class if not specified otherwise
@@ -1118,6 +1113,9 @@ def add_code_sample_docstrings(
         else:
             raise ValueError(f"Docstring can't be built for model {model_class}")
 
+        code_sample = filter_outputs_from_example(
+            code_sample, expected_output=expected_output, expected_loss=expected_loss
+        )
         func_doc = (fn.__doc__ or "") + "".join(docstr)
         output_doc = "" if output_type is None else _prepare_output_docstrings(output_type, config_class)
         built_doc = code_sample.format(**doc_kwargs)