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/speech_to_text/test_feature_extraction_speech_to_text.py
View File

@@ -259,9 +259,7 @@ class Speech2TextFeatureExtractionTest(SequenceFeatureExtractionTestMixin, unitt
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"]

4
tests/models/speech_to_text/test_modeling_speech_to_text.py
View File

@@ -793,9 +793,7 @@ class Speech2TextModelIntegrationTests(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"]

4
tests/models/speech_to_text/test_modeling_tf_speech_to_text.py
View File

@@ -587,9 +587,7 @@ class TFSpeech2TextModelIntegrationTests(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"]