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/speecht5/test_feature_extraction_speecht5.py
View File

@@ -380,9 +380,7 @@ class SpeechT5FeatureExtractionTest(SequenceFeatureExtractionTestMixin, unittest
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"]

8
tests/models/speecht5/test_modeling_speecht5.py
View File

@@ -744,9 +744,7 @@ class SpeechT5ForSpeechToTextIntegrationTests(unittest.TestCase):
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"]
@@ -1771,9 +1769,7 @@ class SpeechT5ForSpeechToSpeechIntegrationTests(unittest.TestCase):
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"]