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 b7672826ca.

* Pass trust_remote_code in librispeech_asr_dummy docstrings

* Revert "Pin datasets<2.20.0 for examples"

This reverts commit 833fc17a3e.

* 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
This commit is contained in:
Albert Villanova del Moral
2024-06-17 18:29:13 +02:00
committed by GitHub
parent 485fd81471
commit a14b055b65
168 changed files with 804 additions and 410 deletions

View File

@@ -136,7 +136,9 @@ class Pop2PianoFeatureExtractionTest(SequenceFeatureExtractionTestMixin, unittes
self.assertTrue(input_features.extrapolated_beatstep.ndim == 2)
def test_integration(self):
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
)
speech_samples = ds.sort("id").select([0])["audio"]
input_speech = [x["array"] for x in speech_samples][0]
sampling_rate = [x["sampling_rate"] for x in speech_samples][0]

View File

@@ -111,7 +111,9 @@ class Pop2PianoProcessorTest(unittest.TestCase):
def get_inputs(self):
"""get inputs for both feature extractor and tokenizer"""
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
)
speech_samples = ds.sort("id").select([0])["audio"]
input_speech = [x["array"] for x in speech_samples][0]
sampling_rate = [x["sampling_rate"] for x in speech_samples][0]