Skip to content

SeamlessM4TProcessorTest::test_save_load_pretrained_addition #42562

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Dec 2, 2025
Merged

SeamlessM4TProcessorTest::test_save_load_pretrained_addition #42562

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 0 additions & 19 deletions tests/models/seamless_m4t/test_processing_seamless_m4t.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,25 +57,6 @@ def test_save_load_pretrained_default(self):
self.assertEqual(processor.feature_extractor.to_json_string(), feature_extractor.to_json_string())
self.assertIsInstance(processor.feature_extractor, SeamlessM4TFeatureExtractor)

def test_save_load_pretrained_additional_features(self):
processor = SeamlessM4TProcessor(
tokenizer=self.get_tokenizer(), feature_extractor=self.get_feature_extractor()
)
processor.save_pretrained(self.tmpdirname)
tokenizer_add_kwargs = self.get_tokenizer(bos_token="(BOS)", eos_token="(EOS)")
feature_extractor_add_kwargs = self.get_feature_extractor(do_normalize=False, padding_value=1.0)

processor = SeamlessM4TProcessor.from_pretrained(
self.tmpdirname, bos_token="(BOS)", eos_token="(EOS)", do_normalize=False, padding_value=1.0
)

self.assertEqual(processor.feature_extractor.to_json_string(), feature_extractor_add_kwargs.to_json_string())
self.assertIsInstance(processor.feature_extractor, SeamlessM4TFeatureExtractor)
self.assertEqual(processor.tokenizer.get_vocab(), tokenizer_add_kwargs.get_vocab())

tokenizer_instance = isinstance(processor.tokenizer, (SeamlessM4TTokenizerFast, SeamlessM4TTokenizer))
self.assertTrue(tokenizer_instance)

# Copied from test.models.whisper.test_processing_whisper.WhisperProcessorTest.test_feature_extractor with Whisper->SeamlessM4T
def test_feature_extractor(self):
feature_extractor = self.get_feature_extractor()
Expand Down