SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Remove trust_remote_code when loading Libri Dummy (#31748)

Browse Source 
* [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
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/models/clvp/test_feature_extraction_clvp.py
View File

@@ -209,9 +209,7 @@ class ClvpFeatureExtractionTest(SequenceFeatureExtractionTestMixin, unittest.Tes
self.assertTrue(pt_processed.input_features.dtype == torch.float32)
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")
ds = ds.cast_column("audio", Audio(sampling_rate=22050))
# automatic decoding with librispeech
speech_samples = ds.sort("id").select(range(num_samples))[:num_samples]["audio"]

8
tests/models/clvp/test_modeling_clvp.py
View File

@@ -371,9 +371,7 @@ class ClvpModelForConditionalGenerationTester:
def prepare_config_and_inputs(self):
_, input_ids, attention_mask = self.clvp_encoder_tester.prepare_config_and_inputs()
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()
@@ -555,9 +553,7 @@ class ClvpModelForConditionalGenerationTest(ModelTesterMixin, unittest.TestCase)
class ClvpIntegrationTest(unittest.TestCase):
def setUp(self):
self.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))
_, self.speech_samples, self.sr = ds.sort("id").select(range(1))[:1]["audio"][0].values()