Pass datasets trust_remote_code (#31406)

* Pass datasets trust_remote_code

* Pass trust_remote_code in more tests

* Add trust_remote_dataset_code arg to some tests

* Revert "Temporarily pin datasets upper version to fix CI"

This reverts commit b7672826.

* Pass trust_remote_code in librispeech_asr_dummy docstrings

* Revert "Pin datasets<2.20.0 for examples"

This reverts commit 833fc17a.

* Pass trust_remote_code to all examples

* Revert "Add trust_remote_dataset_code arg to some tests" to research_projects

* Pass trust_remote_code to tests

* Pass trust_remote_code to docstrings

* Fix flax examples tests requirements

* Pass trust_remote_dataset_code arg to tests

* Replace trust_remote_dataset_code with trust_remote_code in one example

* Fix duplicate trust_remote_code

* Replace args.trust_remote_dataset_code with args.trust_remote_code

* Replace trust_remote_dataset_code with trust_remote_code in parser

* Replace trust_remote_dataset_code with trust_remote_code in dataclasses

* Replace trust_remote_dataset_code with trust_remote_code arg

src/transformers/models/layoutlm/modeling_tf_layoutlm.py

@@ -1601,7 +1601,7 @@ class TFLayoutLMForQuestionAnswering(TFLayoutLMPreTrainedModel, TFQuestionAnswer
         >>> tokenizer = AutoTokenizer.from_pretrained("impira/layoutlm-document-qa", add_prefix_space=True)
         >>> model = TFLayoutLMForQuestionAnswering.from_pretrained("impira/layoutlm-document-qa", revision="1e3ebac")
 
-        >>> dataset = load_dataset("nielsr/funsd", split="train")
+        >>> dataset = load_dataset("nielsr/funsd", split="train", trust_remote_code=True)
         >>> example = dataset[0]
         >>> question = "what's his name?"
         >>> words = example["words"]

src/transformers/models/layoutlmv2/modeling_layoutlmv2.py

@@ -838,7 +838,7 @@ class LayoutLMv2Model(LayoutLMv2PreTrainedModel):
         >>> model = LayoutLMv2Model.from_pretrained("microsoft/layoutlmv2-base-uncased")
 
 
-        >>> dataset = load_dataset("hf-internal-testing/fixtures_docvqa")
+        >>> dataset = load_dataset("hf-internal-testing/fixtures_docvqa", trust_remote_code=True)
         >>> image_path = dataset["test"][0]["file"]
         >>> image = Image.open(image_path).convert("RGB")
 
@@ -1005,7 +1005,7 @@ class LayoutLMv2ForSequenceClassification(LayoutLMv2PreTrainedModel):
 
         >>> set_seed(0)
 
-        >>> dataset = load_dataset("rvl_cdip", split="train", streaming=True)
+        >>> dataset = load_dataset("aharley/rvl_cdip", split="train", streaming=True, trust_remote_code=True)
         >>> data = next(iter(dataset))
         >>> image = data["image"].convert("RGB")
 
@@ -1184,7 +1184,7 @@ class LayoutLMv2ForTokenClassification(LayoutLMv2PreTrainedModel):
 
         >>> set_seed(0)
 
-        >>> datasets = load_dataset("nielsr/funsd", split="test")
+        >>> datasets = load_dataset("nielsr/funsd", split="test", trust_remote_code=True)
         >>> labels = datasets.features["ner_tags"].feature.names
         >>> id2label = {v: k for v, k in enumerate(labels)}
 
@@ -1328,7 +1328,7 @@ class LayoutLMv2ForQuestionAnswering(LayoutLMv2PreTrainedModel):
         >>> processor = AutoProcessor.from_pretrained("microsoft/layoutlmv2-base-uncased")
         >>> model = LayoutLMv2ForQuestionAnswering.from_pretrained("microsoft/layoutlmv2-base-uncased")
 
-        >>> dataset = load_dataset("hf-internal-testing/fixtures_docvqa")
+        >>> dataset = load_dataset("hf-internal-testing/fixtures_docvqa", trust_remote_code=True)
         >>> image_path = dataset["test"][0]["file"]
         >>> image = Image.open(image_path).convert("RGB")
         >>> question = "When is coffee break?"

src/transformers/models/layoutlmv3/modeling_layoutlmv3.py

@@ -859,7 +859,7 @@ class LayoutLMv3Model(LayoutLMv3PreTrainedModel):
         >>> processor = AutoProcessor.from_pretrained("microsoft/layoutlmv3-base", apply_ocr=False)
         >>> model = AutoModel.from_pretrained("microsoft/layoutlmv3-base")
 
-        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train")
+        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train", trust_remote_code=True)
         >>> example = dataset[0]
         >>> image = example["image"]
         >>> words = example["tokens"]
@@ -1075,7 +1075,7 @@ class LayoutLMv3ForTokenClassification(LayoutLMv3PreTrainedModel):
         >>> processor = AutoProcessor.from_pretrained("microsoft/layoutlmv3-base", apply_ocr=False)
         >>> model = AutoModelForTokenClassification.from_pretrained("microsoft/layoutlmv3-base", num_labels=7)
 
-        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train")
+        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train", trust_remote_code=True)
         >>> example = dataset[0]
         >>> image = example["image"]
         >>> words = example["tokens"]
@@ -1191,7 +1191,7 @@ class LayoutLMv3ForQuestionAnswering(LayoutLMv3PreTrainedModel):
         >>> processor = AutoProcessor.from_pretrained("microsoft/layoutlmv3-base", apply_ocr=False)
         >>> model = AutoModelForQuestionAnswering.from_pretrained("microsoft/layoutlmv3-base")
 
-        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train")
+        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train", trust_remote_code=True)
         >>> example = dataset[0]
         >>> image = example["image"]
         >>> question = "what's his name?"
@@ -1311,7 +1311,7 @@ class LayoutLMv3ForSequenceClassification(LayoutLMv3PreTrainedModel):
         >>> processor = AutoProcessor.from_pretrained("microsoft/layoutlmv3-base", apply_ocr=False)
         >>> model = AutoModelForSequenceClassification.from_pretrained("microsoft/layoutlmv3-base")
 
-        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train")
+        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train", trust_remote_code=True)
         >>> example = dataset[0]
         >>> image = example["image"]
         >>> words = example["tokens"]

src/transformers/models/layoutlmv3/modeling_tf_layoutlmv3.py

@@ -1296,7 +1296,7 @@ class TFLayoutLMv3Model(TFLayoutLMv3PreTrainedModel):
         >>> processor = AutoProcessor.from_pretrained("microsoft/layoutlmv3-base", apply_ocr=False)
         >>> model = TFAutoModel.from_pretrained("microsoft/layoutlmv3-base")
 
-        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train")
+        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train", trust_remote_code=True)
         >>> example = dataset[0]
         >>> image = example["image"]
         >>> words = example["tokens"]
@@ -1439,7 +1439,7 @@ class TFLayoutLMv3ForSequenceClassification(TFLayoutLMv3PreTrainedModel, TFSeque
         >>> processor = AutoProcessor.from_pretrained("microsoft/layoutlmv3-base", apply_ocr=False)
         >>> model = TFAutoModelForSequenceClassification.from_pretrained("microsoft/layoutlmv3-base")
 
-        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train")
+        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train", trust_remote_code=True)
         >>> example = dataset[0]
         >>> image = example["image"]
         >>> words = example["tokens"]
@@ -1566,7 +1566,7 @@ class TFLayoutLMv3ForTokenClassification(TFLayoutLMv3PreTrainedModel, TFTokenCla
         >>> processor = AutoProcessor.from_pretrained("microsoft/layoutlmv3-base", apply_ocr=False)
         >>> model = TFAutoModelForTokenClassification.from_pretrained("microsoft/layoutlmv3-base", num_labels=7)
 
-        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train")
+        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train", trust_remote_code=True)
         >>> example = dataset[0]
         >>> image = example["image"]
         >>> words = example["tokens"]
@@ -1703,7 +1703,7 @@ class TFLayoutLMv3ForQuestionAnswering(TFLayoutLMv3PreTrainedModel, TFQuestionAn
         >>> processor = AutoProcessor.from_pretrained("microsoft/layoutlmv3-base", apply_ocr=False)
         >>> model = TFAutoModelForQuestionAnswering.from_pretrained("microsoft/layoutlmv3-base")
 
-        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train")
+        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train", trust_remote_code=True)
         >>> example = dataset[0]
         >>> image = example["image"]
         >>> question = "what's his name?"

src/transformers/models/lilt/modeling_lilt.py

@@ -729,7 +729,7 @@ class LiltModel(LiltPreTrainedModel):
         >>> tokenizer = AutoTokenizer.from_pretrained("SCUT-DLVCLab/lilt-roberta-en-base")
         >>> model = AutoModel.from_pretrained("SCUT-DLVCLab/lilt-roberta-en-base")
 
-        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train")
+        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train", trust_remote_code=True)
         >>> example = dataset[0]
         >>> words = example["tokens"]
         >>> boxes = example["bboxes"]
@@ -868,7 +868,7 @@ class LiltForSequenceClassification(LiltPreTrainedModel):
         >>> tokenizer = AutoTokenizer.from_pretrained("SCUT-DLVCLab/lilt-roberta-en-base")
         >>> model = AutoModelForSequenceClassification.from_pretrained("SCUT-DLVCLab/lilt-roberta-en-base")
 
-        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train")
+        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train", trust_remote_code=True)
         >>> example = dataset[0]
         >>> words = example["tokens"]
         >>> boxes = example["bboxes"]
@@ -987,7 +987,7 @@ class LiltForTokenClassification(LiltPreTrainedModel):
         >>> tokenizer = AutoTokenizer.from_pretrained("SCUT-DLVCLab/lilt-roberta-en-base")
         >>> model = AutoModelForTokenClassification.from_pretrained("SCUT-DLVCLab/lilt-roberta-en-base")
 
-        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train")
+        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train", trust_remote_code=True)
         >>> example = dataset[0]
         >>> words = example["tokens"]
         >>> boxes = example["bboxes"]
@@ -1116,7 +1116,7 @@ class LiltForQuestionAnswering(LiltPreTrainedModel):
         >>> tokenizer = AutoTokenizer.from_pretrained("SCUT-DLVCLab/lilt-roberta-en-base")
         >>> model = AutoModelForQuestionAnswering.from_pretrained("SCUT-DLVCLab/lilt-roberta-en-base")
 
-        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train")
+        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train", trust_remote_code=True)
         >>> example = dataset[0]
         >>> words = example["tokens"]
         >>> boxes = example["bboxes"]

src/transformers/models/speech_encoder_decoder/modeling_speech_encoder_decoder.py

@@ -463,7 +463,7 @@ class SpeechEncoderDecoderModel(PreTrainedModel):
         >>> processor = AutoProcessor.from_pretrained("facebook/wav2vec2-xls-r-300m-en-to-15")
         >>> model = SpeechEncoderDecoderModel.from_pretrained("facebook/wav2vec2-xls-r-300m-en-to-15")
 
-        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
 
         >>> input_values = processor(ds[0]["audio"]["array"], return_tensors="pt").input_values
         >>> # Inference: Translate English speech to German

src/transformers/models/speech_to_text/modeling_speech_to_text.py

@@ -1129,7 +1129,7 @@ class Speech2TextModel(Speech2TextPreTrainedModel):
 
          >>> model = Speech2TextModel.from_pretrained("facebook/s2t-small-librispeech-asr")
          >>> feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/s2t-small-librispeech-asr")
-         >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+         >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
          >>> inputs = feature_extractor(
          ...     ds[0]["audio"]["array"], sampling_rate=ds[0]["audio"]["sampling_rate"], return_tensors="pt"
          ... )
@@ -1270,7 +1270,7 @@ class Speech2TextForConditionalGeneration(Speech2TextPreTrainedModel):
         >>> processor = Speech2TextProcessor.from_pretrained("facebook/s2t-small-librispeech-asr")
 
 
-        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
 
         >>> inputs = processor(
         ...     ds[0]["audio"]["array"], sampling_rate=ds[0]["audio"]["sampling_rate"], return_tensors="pt"

src/transformers/models/speech_to_text/modeling_tf_speech_to_text.py

@@ -1483,7 +1483,7 @@ class TFSpeech2TextForConditionalGeneration(TFSpeech2TextPreTrainedModel, TFCaus
         ...     return batch
 
 
-        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
         >>> ds = ds.map(map_to_array)
         >>> ds.set_format(type="tf")
 

src/transformers/models/speecht5/modeling_speecht5.py

@@ -2338,7 +2338,7 @@ class SpeechT5ForSpeechToText(SpeechT5PreTrainedModel):
         >>> from datasets import load_dataset
 
         >>> dataset = load_dataset(
-        ...     "hf-internal-testing/librispeech_asr_demo", "clean", split="validation"
+        ...     "hf-internal-testing/librispeech_asr_demo", "clean", split="validation", trust_remote_code=True
         ... )  # doctest: +IGNORE_RESULT
         >>> dataset = dataset.sort("id")
         >>> sampling_rate = dataset.features["audio"].sampling_rate
@@ -3024,7 +3024,7 @@ class SpeechT5ForSpeechToSpeech(SpeechT5PreTrainedModel):
         >>> import torch
 
         >>> dataset = load_dataset(
-        ...     "hf-internal-testing/librispeech_asr_demo", "clean", split="validation"
+        ...     "hf-internal-testing/librispeech_asr_demo", "clean", split="validation", trust_remote_code=True
         ... )  # doctest: +IGNORE_RESULT
         >>> dataset = dataset.sort("id")
         >>> sampling_rate = dataset.features["audio"].sampling_rate

src/transformers/models/udop/modeling_udop.py

@@ -1602,7 +1602,7 @@ class UdopModel(UdopPreTrainedModel):
 
         >>> # load an example image, along with the words and coordinates
         >>> # which were extracted using an OCR engine
-        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train")
+        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train", trust_remote_code=True)
         >>> example = dataset[0]
         >>> image = example["image"]
         >>> words = example["tokens"]
@@ -1781,7 +1781,7 @@ class UdopForConditionalGeneration(UdopPreTrainedModel):
 
         >>> # load an example image, along with the words and coordinates
         >>> # which were extracted using an OCR engine
-        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train")
+        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train", trust_remote_code=True)
         >>> example = dataset[0]
         >>> image = example["image"]
         >>> words = example["tokens"]
@@ -2009,7 +2009,7 @@ class UdopEncoderModel(UdopPreTrainedModel):
 
         >>> # load an example image, along with the words and coordinates
         >>> # which were extracted using an OCR engine
-        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train")
+        >>> dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train", trust_remote_code=True)
         >>> example = dataset[0]
         >>> image = example["image"]
         >>> words = example["tokens"]

src/transformers/models/univnet/modeling_univnet.py

@@ -525,7 +525,7 @@ class UnivNetModel(PreTrainedModel):
          >>> model = UnivNetModel.from_pretrained("dg845/univnet-dev")
          >>> feature_extractor = UnivNetFeatureExtractor.from_pretrained("dg845/univnet-dev")
 
-         >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+         >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
          >>> # Resample the audio to the feature extractor's sampling rate.
          >>> ds = ds.cast_column("audio", Audio(sampling_rate=feature_extractor.sampling_rate))
          >>> inputs = feature_extractor(

src/transformers/models/wav2vec2/modeling_flax_wav2vec2.py

@@ -1076,7 +1076,7 @@ FLAX_WAV2VEC2_MODEL_DOCSTRING = """
     ...     return batch
 
 
-    >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+    >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
     >>> ds = ds.map(map_to_array)
 
     >>> input_values = processor(
@@ -1195,7 +1195,7 @@ FLAX_WAV2VEC2_FOR_CTC_DOCSTRING = """
     ...     return batch
 
 
-    >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+    >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
     >>> ds = ds.map(map_to_array)
 
     >>> input_values = processor(
@@ -1396,7 +1396,7 @@ FLAX_WAV2VEC2_FOR_PRETRAINING_DOCSTRING = """
     ...     return batch
 
 
-    >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+    >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
     >>> ds = ds.map(map_to_array)
 
     >>> input_values = feature_extractor(ds["speech"][0], return_tensors="np").input_values  # Batch size 1

src/transformers/models/wav2vec2/modeling_tf_wav2vec2.py

@@ -1542,7 +1542,7 @@ class TFWav2Vec2Model(TFWav2Vec2PreTrainedModel):
         ...     return batch
 
 
-        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
         >>> ds = ds.map(map_to_array)
 
         >>> input_values = processor(ds["speech"][0], return_tensors="tf").input_values  # Batch size 1
@@ -1654,7 +1654,7 @@ class TFWav2Vec2ForCTC(TFWav2Vec2PreTrainedModel):
         ...     return batch
 
 
-        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
         >>> ds = ds.map(map_to_array)
 
         >>> input_values = processor(ds["speech"][0], return_tensors="tf").input_values  # Batch size 1

src/transformers/models/wav2vec2/modeling_wav2vec2.py

@@ -2045,7 +2045,7 @@ class Wav2Vec2ForPreTraining(Wav2Vec2PreTrainedModel):
         >>> feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/wav2vec2-base")
         >>> model = Wav2Vec2ForPreTraining.from_pretrained("facebook/wav2vec2-base")
 
-        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
         >>> input_values = feature_extractor(ds[0]["audio"]["array"], return_tensors="pt").input_values  # Batch size 1
 
         >>> # compute masked indices

src/transformers/models/wav2vec2/tokenization_wav2vec2.py

@@ -590,7 +590,7 @@ class Wav2Vec2CTCTokenizer(PreTrainedTokenizer):
         >>> feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/wav2vec2-base-960h")
 
         >>> # load first sample of English common_voice
-        >>> dataset = load_dataset("mozilla-foundation/common_voice_11_0", "en", split="train", streaming=True)
+        >>> dataset = load_dataset("mozilla-foundation/common_voice_11_0", "en", split="train", streaming=True, trust_remote_code=True)
         >>> dataset = dataset.cast_column("audio", datasets.Audio(sampling_rate=16_000))
         >>> dataset_iter = iter(dataset)
         >>> sample = next(dataset_iter)

src/transformers/models/wav2vec2_conformer/modeling_wav2vec2_conformer.py

@@ -1453,7 +1453,7 @@ class Wav2Vec2ConformerForPreTraining(Wav2Vec2ConformerPreTrainedModel):
         >>> feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/wav2vec2-conformer-rel-pos-large")
         >>> model = Wav2Vec2ConformerForPreTraining.from_pretrained("facebook/wav2vec2-conformer-rel-pos-large")
 
-        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
         >>> input_values = feature_extractor(ds[0]["audio"]["array"], return_tensors="pt").input_values  # Batch size 1
 
         >>> # compute masked indices

src/transformers/models/wav2vec2_with_lm/processing_wav2vec2_with_lm.py

@@ -545,7 +545,7 @@ class Wav2Vec2ProcessorWithLM(ProcessorMixin):
         >>> processor = AutoProcessor.from_pretrained("patrickvonplaten/wav2vec2-base-100h-with-lm")
 
         >>> # load first sample of English common_voice
-        >>> dataset = load_dataset("mozilla-foundation/common_voice_11_0", "en", split="train", streaming=True)
+        >>> dataset = load_dataset("mozilla-foundation/common_voice_11_0", "en", split="train", streaming=True, trust_remote_code=True)
         >>> dataset = dataset.cast_column("audio", datasets.Audio(sampling_rate=16_000))
         >>> dataset_iter = iter(dataset)
         >>> sample = next(dataset_iter)

src/transformers/models/whisper/generation_whisper.py

@@ -461,7 +461,7 @@ class WhisperGenerationMixin:
         >>> processor = AutoProcessor.from_pretrained("openai/whisper-tiny.en")
         >>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny.en")
 
-        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
 
         >>> inputs = processor(ds[0]["audio"]["array"], return_tensors="pt")
         >>> input_features = inputs.input_features

src/transformers/models/whisper/modeling_flax_whisper.py

@@ -985,7 +985,7 @@ class FlaxWhisperPreTrainedModel(FlaxPreTrainedModel):
 
         >>> processor = WhisperProcessor.from_pretrained("openai/whisper-tiny.en")
         >>> model = FlaxWhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny.en", from_pt=True)
-        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
         >>> inputs = processor(ds[0]["audio"]["array"], return_tensors="np")
         >>> input_features = inputs.input_features
         >>> encoder_outputs = model.encode(input_features=input_features)
@@ -1045,7 +1045,7 @@ class FlaxWhisperPreTrainedModel(FlaxPreTrainedModel):
 
         >>> processor = WhisperProcessor.from_pretrained("openai/whisper-tiny.en")
         >>> model = FlaxWhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny.en", from_pt=True)
-        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
         >>> input_features = processor(ds[0]["audio"]["array"], return_tensors="np").input_features
 
         >>> encoder_outputs = model.encode(input_features=input_features)
@@ -1297,7 +1297,7 @@ class FlaxWhisperForConditionalGeneration(FlaxWhisperPreTrainedModel):
 
         >>> processor = WhisperProcessor.from_pretrained("openai/whisper-tiny.en")
         >>> model = FlaxWhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny.en", from_pt=True)
-        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
         >>> inputs = processor(ds[0]["audio"]["array"], return_tensors="np")
         >>> input_features = inputs.input_features
         >>> encoder_outputs = model.encode(input_features=input_features)
@@ -1516,7 +1516,7 @@ FLAX_WHISPER_CONDITIONAL_GENERATION_DOCSTRING = r"""
 
     >>> processor = WhisperProcessor.from_pretrained("openai/whisper-tiny.en")
     >>> model = FlaxWhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny.en", from_pt=True)
-    >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+    >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
     >>> inputs = processor(ds[0]["audio"]["array"], return_tensors="np")
     >>> input_features = inputs.input_features
     >>> generated_ids = model.generate(input_ids=input_features)
@@ -1670,7 +1670,7 @@ FLAX_WHISPER_AUDIO_CLASSIFICATION_DOCSTRING = r"""
     >>> model = FlaxWhisperForAudioClassification.from_pretrained(
     ...     "sanchit-gandhi/whisper-medium-fleurs-lang-id", from_pt=True
     ... )
-    >>> ds = load_dataset("google/fleurs", "all", split="validation", streaming=True)
+    >>> ds = load_dataset("google/fleurs", "all", split="validation", streaming=True, trust_remote_code=True)
 
     >>> sample = next(iter(ds))
 

src/transformers/models/whisper/modeling_tf_whisper.py

@@ -1147,7 +1147,7 @@ class TFWhisperMainLayer(keras.layers.Layer):
 
          >>> model = TFWhisperModel.from_pretrained("openai/whisper-base")
          >>> feature_extractor = AutoFeatureExtractor.from_pretrained("openai/whisper-base")
-         >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+         >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
          >>> inputs = feature_extractor(ds[0]["audio"]["array"], return_tensors="tf")
          >>> input_features = inputs.input_features
          >>> decoder_input_ids = tf.convert_to_tensor([[1, 1]]) * model.config.decoder_start_token_id
@@ -1283,7 +1283,7 @@ class TFWhisperModel(TFWhisperPreTrainedModel):
 
          >>> model = TFWhisperModel.from_pretrained("openai/whisper-base")
          >>> feature_extractor = AutoFeatureExtractor.from_pretrained("openai/whisper-base")
-         >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+         >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
          >>> inputs = feature_extractor(ds[0]["audio"]["array"], return_tensors="tf")
          >>> input_features = inputs.input_features
          >>> decoder_input_ids = tf.convert_to_tensor([[1, 1]]) * model.config.decoder_start_token_id
@@ -1413,7 +1413,7 @@ class TFWhisperForConditionalGeneration(TFWhisperPreTrainedModel, TFCausalLangua
         >>> processor = AutoProcessor.from_pretrained("openai/whisper-tiny.en")
         >>> model = TFWhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny.en")
 
-        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
 
         >>> inputs = processor(ds[0]["audio"]["array"], return_tensors="tf")
         >>> input_features = inputs.input_features