def test_save_load_pretrained_additional_features(self):
processor = MCTCTProcessor(
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 = MCTCTProcessor.from_pretrained(self.tmpdirname,
bos_token="(BOS)",
eos_token="(EOS)",
do_normalize=False,
padding_value=1.0)
self.assertEqual(processor.tokenizer.get_vocab(),
tokenizer_add_kwargs.get_vocab())
self.assertIsInstance(processor.tokenizer, Wav2Vec2CTCTokenizer)
self.assertEqual(processor.feature_extractor.to_json_string(),
feature_extractor_add_kwargs.to_json_string())
self.assertIsInstance(processor.feature_extractor,
MCTCTFeatureExtractor)
def test_save_load_pretrained_default(self):
tokenizer = self.get_tokenizer()
feature_extractor = self.get_feature_extractor()
processor = MCTCTProcessor(tokenizer=tokenizer,
feature_extractor=feature_extractor)
processor.save_pretrained(self.tmpdirname)
processor = MCTCTProcessor.from_pretrained(self.tmpdirname)
self.assertEqual(processor.tokenizer.get_vocab(),
tokenizer.get_vocab())
self.assertIsInstance(processor.tokenizer, Wav2Vec2CTCTokenizer)
self.assertEqual(processor.feature_extractor.to_json_string(),
feature_extractor.to_json_string())
self.assertIsInstance(processor.feature_extractor,
MCTCTFeatureExtractor)