def test_create_unique_root_2():
from utilities.utilities import Utilities
from model.configuration import Configuration
from model.nlp import NLPModel
u = Utilities()
configuration = Configuration()
nlp_model = NLPModel()
root = '12345'
configuration.set_model('video')
configuration.set_use_enhanced(False)
configuration.set_language_code('fr_FR')
configuration.set_alternative_language_codes(['en-US', 'ru-RU'])
configuration.set_speech_context('hi', 5)
nlp_model.set_remove_stop_words(True)
nlp_model.set_apply_stemming(False)
nlp_model.set_expand_contractions(True)
nlp_model.set_n2w(True)
result = u.create_unique_root(root, configuration, nlp_model)
expected = '12345_video_fr_FR_alts_applied_speech_adaptation_applied_boost_5_stop_words_removed_contractions_expanded_numbers_converted_2_words'
assert result == expected
# Generate hyp
speech_to_text = SpeechToText()
if use_fake_hyp:
hyp = 'this is a fake hyp'
elif local_files_path:
file = local_files_path + '/' + audio
hyp = speech_to_text.transcribe_streaming(file, configuration)
else:
hyp = speech_to_text.get_hypothesis(audio, configuration)
logger.debug(f'RAW HYP: {hyp}')
logger.debug(f'RAW REF {ref}')
unique_root = utilities.create_unique_root(root, configuration, nlp_model)
io_handler.write_hyp(file_name=unique_root + '.txt', text=hyp)
if not only_transcribe:
# Calculate WER
wer_obj = SimpleWER()
if process_each_letter:
logger.debug('PROCESSING EACH CHARACTER')
hyp = list(hyp)
hyp = ' '.join(hyp)
ref = list(ref)
ref = ' '.join(ref)
logger.debug(f'HYP FOR WER: {hyp}')
logger.debug(f'REF FOR WER: {ref}')
