Remove `trust_remote_code` when loading Libri Dummy (#31748)

* [whisper integration] use parquet dataset for testing

* propagate to others

* more propagation

* last one

src/transformers/commands/pt_to_tf.py

@@ -202,9 +202,7 @@ class PTtoTFCommand(BaseTransformersCLICommand):
         """
 
         def _get_audio_input():
-            ds = load_dataset(
-                "hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True
-            )
+            ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
             speech_samples = ds.sort("id").select(range(2))[:2]["audio"]
             raw_samples = [x["array"] for x in speech_samples]
             return raw_samples

src/transformers/generation/logits_process.py

@@ -1760,7 +1760,7 @@ class SuppressTokensAtBeginLogitsProcessor(LogitsProcessor):
 
     >>> 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", trust_remote_code=True)
+    >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
     >>> inputs = processor(ds[0]["audio"]["array"], return_tensors="pt")
 
     >>> # Whisper has `begin_suppress_tokens` set by default (= `[220, 50256]`). 50256 is the EOS token, so this means
@@ -1812,7 +1812,7 @@ class SuppressTokensLogitsProcessor(LogitsProcessor):
 
     >>> 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", trust_remote_code=True)
+    >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
     >>> inputs = processor(ds[0]["audio"]["array"], return_tensors="pt")
 
     >>> # Whisper has a long list of suppressed tokens. For instance, in this case, the token 1 is suppressed by default.
@@ -1901,7 +1901,7 @@ class WhisperTimeStampLogitsProcessor(LogitsProcessor):
 
     >>> 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", trust_remote_code=True)
+    >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
     >>> inputs = processor(ds[3]["audio"]["array"], return_tensors="pt")
     >>> input_features = inputs.input_features
 

src/transformers/models/clvp/modeling_clvp.py

@@ -1681,7 +1681,7 @@ class ClvpModelForConditionalGeneration(ClvpPreTrainedModel):
 
         >>> # Define the Text and Load the Audio (We are taking an audio example from HuggingFace Hub using `datasets` library)
         >>> text = "This is an example text."
-        >>> ds = datasets.load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
+        >>> ds = datasets.load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> ds = ds.cast_column("audio", datasets.Audio(sampling_rate=22050))
         >>> _, audio, sr = ds.sort("id").select(range(1))[:1]["audio"][0].values()
 
@@ -1754,7 +1754,7 @@ class ClvpModelForConditionalGeneration(ClvpPreTrainedModel):
         >>> # Define the Text and Load the Audio (We are taking an audio example from HuggingFace Hub using `datasets` library)
         >>> text = "This is an example text."
 
-        >>> ds = datasets.load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
+        >>> ds = datasets.load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> ds = ds.cast_column("audio", datasets.Audio(sampling_rate=22050))
         >>> _, audio, sr = ds.sort("id").select(range(1))[:1]["audio"][0].values()
 

src/transformers/models/deprecated/speech_to_text_2/modeling_speech_to_text_2.py

@@ -831,7 +831,7 @@ class Speech2Text2ForCausalLM(Speech2Text2PreTrainedModel):
         >>> model.config.decoder_start_token_id = tokenizer.bos_token_id
         >>> # pre-process inputs and labels
 
-        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> inputs = feature_extractor(
         ...     ds[0]["audio"]["array"], sampling_rate=ds[0]["audio"]["sampling_rate"], return_tensors="pt"
         ... )

src/transformers/models/hubert/modeling_hubert.py

@@ -1325,7 +1325,7 @@ class HubertModel(HubertPreTrainedModel):
         ...     return batch
 
 
-        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> ds = ds.map(map_to_array)
 
         >>> input_values = processor(ds["speech"][0], return_tensors="pt").input_values  # Batch size 1

src/transformers/models/hubert/modeling_tf_hubert.py

@@ -1471,7 +1471,7 @@ class TFHubertModel(TFHubertPreTrainedModel):
         ...     return batch
 
 
-        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> ds = ds.map(map_to_array)
 
         >>> input_values = processor(ds["speech"][0], return_tensors="tf").input_values  # Batch size 1
@@ -1583,7 +1583,7 @@ class TFHubertForCTC(TFHubertPreTrainedModel):
         ...     return batch
 
 
-        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> ds = ds.map(map_to_array)
 
         >>> input_values = processor(ds["speech"][0], return_tensors="tf").input_values  # Batch size 1

src/transformers/models/speech_encoder_decoder/modeling_speech_encoder_decoder.py

@@ -464,7 +464,7 @@ 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", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
 
         >>> 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", trust_remote_code=True)
+         >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
          >>> 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", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
 
         >>> 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", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> ds = ds.map(map_to_array)
         >>> ds.set_format(type="tf")
 

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", trust_remote_code=True)
+         >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
          >>> # 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", trust_remote_code=True)
+    >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
     >>> 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", trust_remote_code=True)
+    >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
     >>> 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", trust_remote_code=True)
+    >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
     >>> 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", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> 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", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> 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

@@ -1938,7 +1938,7 @@ 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", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> input_values = feature_extractor(ds[0]["audio"]["array"], return_tensors="pt").input_values  # Batch size 1
 
         >>> # compute masked indices

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", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> input_values = feature_extractor(ds[0]["audio"]["array"], return_tensors="pt").input_values  # Batch size 1
 
         >>> # compute masked indices

src/transformers/models/whisper/generation_whisper.py

@@ -464,7 +464,7 @@ 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", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
 
         >>> 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", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> 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", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> 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", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> 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", trust_remote_code=True)
+    >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
     >>> inputs = processor(ds[0]["audio"]["array"], return_tensors="np")
     >>> input_features = inputs.input_features
     >>> generated_ids = model.generate(input_ids=input_features)

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", trust_remote_code=True)
+         >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
          >>> 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", trust_remote_code=True)
+         >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
          >>> 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", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
 
         >>> inputs = processor(ds[0]["audio"]["array"], return_tensors="tf")
         >>> input_features = inputs.input_features

src/transformers/models/whisper/modeling_whisper.py

@@ -1555,7 +1555,7 @@ class WhisperModel(WhisperPreTrainedModel):
 
          >>> model = WhisperModel.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", trust_remote_code=True)
+         >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
          >>> inputs = feature_extractor(ds[0]["audio"]["array"], return_tensors="pt")
          >>> input_features = inputs.input_features
          >>> decoder_input_ids = torch.tensor([[1, 1]]) * model.config.decoder_start_token_id
@@ -1698,7 +1698,7 @@ class WhisperForConditionalGeneration(WhisperGenerationMixin, WhisperPreTrainedM
         >>> 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", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
 
         >>> inputs = processor(ds[0]["audio"]["array"], return_tensors="pt")
         >>> input_features = inputs.input_features
@@ -1959,7 +1959,7 @@ class WhisperForCausalLM(WhisperPreTrainedModel):
 
         >>> assistant_model = WhisperForCausalLM.from_pretrained("distil-whisper/distil-large-v2")
 
-        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True)
+        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> sample = ds[0]["audio"]
         >>> input_features = processor(
         ...     sample["array"], sampling_rate=sample["sampling_rate"], return_tensors="pt"

tests/models/audio_spectrogram_transformer/test_feature_extraction_audio_spectrogram_transformer.py

@@ -153,9 +153,7 @@ class ASTFeatureExtractionTest(SequenceFeatureExtractionTestMixin, unittest.Test
     def _load_datasamples(self, num_samples):
         from datasets import load_dataset
 
-        ds = load_dataset(
-            "hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True
-        )
+        ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         # automatic decoding with librispeech
         speech_samples = ds.sort("id").select(range(num_samples))[:num_samples]["audio"]
 

tests/models/clap/test_feature_extraction_clap.py

@@ -164,9 +164,7 @@ class ClapFeatureExtractionTest(SequenceFeatureExtractionTestMixin, unittest.Tes
 
     # Copied from tests.models.whisper.test_feature_extraction_whisper.WhisperFeatureExtractionTest._load_datasamples
     def _load_datasamples(self, num_samples):
-        ds = load_dataset(
-            "hf-internal-testing/librispeech_asr_dummy", "clean", split="validation", trust_remote_code=True
-        )
+        ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         # automatic decoding with librispeech
         speech_samples = ds.sort("id").select(range(num_samples))[:num_samples]["audio"]