Remove trust_remote_code when loading Libri Dummy (#31748)

* [whisper integration] use parquet dataset for testing

* propagate to others

* more propagation

* last one
This commit is contained in:
Sanchit Gandhi
2024-07-23 14:54:38 +08:00
committed by GitHub
parent 3aefb4ec7f
commit f83c6f1d02
56 changed files with 110 additions and 254 deletions

View File

@@ -136,9 +136,7 @@ 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", trust_remote_code=True
)
ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
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

@@ -111,9 +111,7 @@ 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", trust_remote_code=True
)
ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
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]