def test_set_then_get_language_code():
from model.configuration import Configuration
config = Configuration()
expected = 'fr-FR'
config.set_language_code(expected)
result = config.get_language_code()
assert result == expected
def test_str():
from model.configuration import Configuration
config = Configuration()
expected_model = 'phone_call'
expected_language_code = 'hi-IN'
expected_use_enhanced = True
expected_sample_rate_hertz = 48000
expected_audio_channel_count = 5
expected_enable_separate_recognition_per_channel = False
expected_boost = 6
expected_phrases = ['testing', '$ADDRESSNUM']
config.set_model(expected_model)
config.set_language_code(expected_language_code)
config.set_enable_separate_recognition_per_channel(
expected_enable_separate_recognition_per_channel)
config.set_audio_channel_count(expected_audio_channel_count)
config.set_use_enhanced(expected_use_enhanced)
config.set_sample_rate_hertz(expected_sample_rate_hertz)
config.set_speech_context(expected_phrases, expected_boost)
result = config.__str__()
assert isinstance(result, str)
assert expected_model in result
assert expected_language_code in result
assert str(expected_use_enhanced) in result
assert str(expected_sample_rate_hertz) in result
assert str(expected_audio_channel_count) in result
assert str(expected_enable_separate_recognition_per_channel) in result
assert str(expected_boost) in result
def test_get_hypothesis():
from model.configuration import Configuration
from utilities.speech_to_text import SpeechToText
uri = 'gs://brb/test_audio_n_truth/1.wav'
configuration_object = Configuration()
configuration_object.set_language_code('en-US')
configuration_object.set_encoding('LINEAR16')
configuration_object.set_sample_rate_hertz(44100)
configuration_object.set_model('default')
speech = SpeechToText()
result = speech.get_hypothesis(uri, configuration_object)
expected = ' testing 1 2 3 hello hello testing one two three'
assert result == expected
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
def test_update_csv():
from utilities.io_handler import IOHandler
from model.configuration import Configuration
from model.nlp import NLPModel
import os
configuration = Configuration()
nlp_model = NLPModel()
io = IOHandler()
result_file_name = io._result_file_name
io.set_result_path('test_results_path')
io.write_csv_header()
expected_uri = 'gs://foo/bar/baz/test.flac'
expected_lang = 'fr-FR'
nlp_model.set_apply_stemming(True)
configuration.set_language_code(expected_lang)
io.update_csv(expected_uri, configuration, nlp_model)
full_path = f'{io.get_result_path()}/{result_file_name}'
with open(full_path, 'r') as file:
contents = file.read()
os.remove(full_path)
assert expected_uri in contents
assert expected_lang in contents
assert 'True' in contents
string = f'Running with phrase hints, boost {boost}'
else:
string = 'No speech context applied'
print(string)
logger.debug(string)
if phrases:
configuration.set_speech_context(phrases, boost)
else:
configuration.set_speech_context([], 0)
if alt_run:
configuration.set_alternative_language_codes(alternative_language_codes)
configuration.set_model(model)
configuration.set_sample_rate_hertz(sample_rate_hertz)
configuration.set_language_code(language)
configuration.set_encoding(encoding)
if audio_channel_count > 1:
configuration.set_audio_channel_count(audio_channel_count)
configuration.set_enable_separate_recognition_per_channel(True)
logger.debug(f'CONFIGURATION: {configuration}')
print(f'STARTING')
msg = f'audio: {audio}, {configuration}'
logger.debug(msg)
print(msg)
# Generate hyp
speech_to_text = SpeechToText()
def test_set_language_code():
from model.configuration import Configuration
config = Configuration()
config.set_language_code('en-US')
