def test_apply_nlp_options_stop():
from utilities.nlp_options import NLPOptions
from model.nlp import NLPModel
hyp = 'thingy in the dancing'
options = NLPOptions()
model = NLPModel()
model.set_remove_stop_words(True)
result = options.apply_nlp_options(model, hyp)
expected = ' thingy dancing'
assert result == expected
def test_apply_nlp_options_n2w():
from utilities.nlp_options import NLPOptions
from model.nlp import NLPModel
hyp = '34 567'
options = NLPOptions()
model = NLPModel()
model.set_n2w(True)
result = options.apply_nlp_options(model, hyp)
expected = ' thirty-four five hundred and sixty-seven'
assert result == expected
def test_apply_nlp_options_expand_cont():
from utilities.nlp_options import NLPOptions
from model.nlp import NLPModel
hyp = "isn't can't"
options = NLPOptions()
model = NLPModel()
model.set_expand_contractions(True)
result = options.apply_nlp_options(model, hyp)
expected = 'is not cannot'
assert result == expected
def test_apply_nlp_options_stem():
from utilities.nlp_options import NLPOptions
from model.nlp import NLPModel
hyp = 'thingy dancing'
options = NLPOptions()
model = NLPModel()
model.set_apply_stemming(True)
result = options.apply_nlp_options(model, hyp)
expected = 'thingi danc '
assert result == expected
def test_stem_stop_n2w_exp():
from utilities.nlp_options import NLPOptions
from model.nlp import NLPModel
hyp = "don't in the won't didn't isn't raining 3 6 9"
options = NLPOptions()
model = NLPModel()
model.set_n2w(True)
model.set_remove_stop_words(True)
model.set_apply_stemming(True)
model.set_expand_contractions(True)
result = options.apply_nlp_options(model, hyp)
expected = 'rain three six nine '
assert result == expected
def test_stem_stop_n2w():
from utilities.nlp_options import NLPOptions
from model.nlp import NLPModel
hyp = "666 don't in the raining"
options = NLPOptions()
model = NLPModel()
model.set_n2w(True)
model.set_remove_stop_words(True)
model.set_apply_stemming(True)
result = options.apply_nlp_options(model, hyp)
expected = 'six hundr sixtysix nt rain '
assert result == expected
def test_apply_nlp_options_stem_n2w_exp():
from utilities.nlp_options import NLPOptions
from model.nlp import NLPModel
hyp = "666 don't in the raining"
options = NLPOptions()
model = NLPModel()
model.set_n2w(True)
model.set_expand_contractions(True)
model.set_apply_stemming(True)
result = options.apply_nlp_options(model, hyp)
expected = 'six hundr and sixty-six do not in the rain '
assert result == expected
def test_apply_nlp_options_stop_n2w_exp():
from utilities.nlp_options import NLPOptions
from model.nlp import NLPModel
hyp = "666 don't in the"
options = NLPOptions()
model = NLPModel()
model.set_n2w(True)
model.set_expand_contractions(True)
model.set_remove_stop_words(True)
result = options.apply_nlp_options(model, hyp)
expected = ' six hundred sixtysix'
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
def test_apply_nlp_options_stem_exp():
from utilities.nlp_options import NLPOptions
from model.nlp import NLPModel
hyp = "thingy dancing won't"
options = NLPOptions()
model = NLPModel()
model.set_apply_stemming(True)
model.set_expand_contractions(True)
result = options.apply_nlp_options(model, hyp)
expected = 'thingi danc will not '
assert result == expected
class IOHandler(object):
_result_path = ''
_result_file_name = 'results.csv'
_csv_header = 'AUDIO_FILE, MODEL, ENHANCED, LANGUAGE, ALTERNATIVE_LANGS, PHRASE_HINTS_APPLIED, BOOST, REF_WORD_COUNT, REF_ERROR_COUNT , WER,STEMMING_APPLIED , STOP_WORDS_REMOVED, NUMBER_TO_WORD_CONVERSION, CONTRACTIONS_EXPANDED, INSERTIONS, DELETIONS, SUBSTITUTIONS, DELETED_WORDS, INSERTED_WORDS, SUBSTITUTE_WORDS\n'
_csv_header_written = False
configuration = Configuration()
nlp_model = NLPModel()
_queue_file_name = 'queue.txt'
def set_queue_file_name(self, name):
self._queue_file_name = name
def get_queue_file_name(self):
return self._queue_file_name
def set_result_path(self, result_path):
self._result_path = result_path
def get_result_path(self):
return self._result_path
def write_csv_header(self):
import os
if not self._csv_header_written:
full_path = f'{self.get_result_path()}/{self._result_file_name}'
# if path does not exists, make it
if not os.path.exists(self.get_result_path()):
os.makedirs(self.get_result_path())
with open(full_path, 'w') as file:
try:
file.write(self._csv_header)
except IOError as i:
print(f'Can not write csv header: {i}')
except FileNotFoundError as x:
print(f'Can not find csv file: {x}')
self._csv_header_written = True
def update_csv(self,
uri,
configuration,
nlp_model,
word_count_list=None,
ref_total_word_count=0,
ref_error_count=0,
word_error_rate=0,
ins=0,
deletions=0,
subs=0):
import logging
logging.basicConfig(filename='wer_app.log')
logger = logging.getLogger(__name__)
from collections import OrderedDict
deleted_words_dict = dict()
inserted_words_dict = dict()
substitute_words_dict = dict()
if word_count_list:
try:
deleted_words_dict = OrderedDict(
sorted(word_count_list[0].items(), key=lambda x: x[1]))
inserted_words_dict = OrderedDict(
sorted(word_count_list[1].items(), key=lambda x: x[1]))
substitute_words_dict = OrderedDict(
sorted(word_count_list[2].items(), key=lambda x: x[1]))
except TypeError as t:
string = f'{t}'
logger.debug(string)
print(string)
deleted_words_dict = None
inserted_words_dict = None
substitute_words_dict = None
deleted_words = ''
inserted_words = ''
substitute_words = ''
if deleted_words_dict:
for k, v in deleted_words_dict.items():
deleted_words += f'{k}:{v}, '
if inserted_words_dict:
for k, v in inserted_words_dict.items():
inserted_words += f'{k}:{v}, '
if substitute_words_dict:
for k, v in substitute_words_dict.items():
substitute_words += f'{k}:{v}, '
full_path = f'{self.get_result_path()}/{self._result_file_name}'
alts = ''
for item in (configuration.get_alternative_language_codes()):
alts += item + ' '
string = f'{uri}, {configuration.get_model()}, {configuration.get_use_enhanced()}, {configuration.get_language_code()},' \
f'{alts}, {bool(configuration.get_phrases())},' \
f'{configuration.get_boost()}, {ref_total_word_count}, {ref_error_count}, {word_error_rate}, {nlp_model.get_apply_stemming()},' \
f'{nlp_model.get_remove_stop_words()}, {nlp_model.get_n2w()}, {nlp_model.get_expand_contractions()}, {ins}, {deletions}, {subs}, ' \
f'{deleted_words}, {inserted_words}, {substitute_words}\n'
with open(
full_path,
'a+',
) as file:
try:
file.write(string)
except IOError as i:
print(f'Can not update csv file: {i}')
print(f'UPDATED: {full_path}')
def write_html_diagnostic(self, wer_obj, unique_root, result_path):
aligned_html = '<br>'.join(wer_obj.aligned_htmls)
result_file = unique_root + '.html'
write_path = f'{result_path}/{result_file}'
with open(write_path, 'w') as f:
try:
f.write(aligned_html)
except IOError as i:
print(f'Can not write html diagnostic {write_path}: {i}')
print(f'WROTE: diagnostic file: {write_path} ')
def write_queue_file(self, data):
try:
with open(self._queue_file_name, 'a+') as f:
if isinstance(data, str):
info = data.split()
else:
info = data
for item in info:
f.write(item + ',')
except IOError as e:
print(f'Can not write diagnostic file: {e}')
def read_queue_file(self):
result = None
try:
with open(self._queue_file_name, 'r') as f:
result = f.read()
except IOError as e:
print(f'Can not read queue file: {e}')
except FileNotFoundError as x:
print(f'Queue file not found: {x}')
if not result:
raise IOError('No contents found in queue')
return result
def write_hyp(self, file_name, text):
import os.path
if not os.path.exists(self.get_result_path()):
os.makedirs(self.get_result_path())
p = f'{self.get_result_path()}/{file_name}'
with open(p, 'w+') as f:
f.write(text)
parser.add_argument('-alts', '--alternative_languages', default=None, nargs='+', required=False,
help="Space separated list of language codes for auto language detection. Example en-IN en-US en-GB")
parser.add_argument('-p', '--phrase_file', required=False, type=str,
help='Path to file containing comma separated phrases')
parser.add_argument('-b', '--boosts', default=list(), nargs='+', required=False,
help=('Space separated list of boost values to evaluate for speech adaptation'))
parser.add_argument('-ch', '--multi', required=False, type=int,
help='Integer indicating the number of channels if more than one')
parser.add_argument('-q', '--random_queue', required=False, action='store_true', help='Replaces default queue.txt with randomly named queue file')
parser.add_argument('-fake', '--fake_hyp', required=False, action='store_true', help='Use a fake hypothesis for testing')
parser.add_argument('-limit', '--limit', required=False, default=None,type= int, help = 'Limit to X number of audio files')
parser.add_argument('-nzb', '--no_zeros_boost', required=False, action='store_true', help='skip boost of 0' )
parser.add_argument('-single', '--single_word', required=False, action='store_true', help='process each letter rather than whole words')
parser.add_argument('-lf','--local_files_path', required=False, type=str, help='process local files', default=None)
nlp_model = NLPModel()
io_handler = IOHandler()
nlp_options = NLPOptions()
configuration = Configuration()
# Turn on punctuation .. why not.. no bearing on WER
configuration.set_enableAutomaticPunctuation(True)
args = parser.parse_args()
no_zeros_for_boost = args.no_zeros_boost
process_each_letter = args.single_word
local_files_path = args.local_files_path
limit = args.limit
cloud_store_uri = args.cloud_store_uri
io_handler.set_result_path(args.local_results_path)
only_transcribe = args.transcriptions_only
nlp_model.set_n2w(args.numbers_to_words)
parser.add_argument('-l', '--langs', default=['en-US'], nargs='+', required=False,
help="Space separated list of language codes. Each processed seperately. Example en-AU en-GB")
parser.add_argument('-alts', '--alternative_languages', default=None, nargs='+', required=False,
help="Space separated list of language codes for auto language detection. Example en-IN en-US en-GB")
parser.add_argument('-p', '--phrase_file', required=False, type=str,
help='Path to file containing comma separated phrases')
parser.add_argument('-b', '--boosts', default=list(), nargs='+', required=False,
help=('Space separated list of boost values to evaluate for speech adaptation'))
parser.add_argument('-ch', '--multi', required=False, type=int,
help='Integer indicating the number of channels if more than one')
parser.add_argument('-a', '--alts2prime', required=False, action='store_true', help='Use each alternative language as a primary language')
parser.add_argument('-q', '--random_queue', required=False, action='store_true', help='Replaces default queue.txt with randomly named queue file')
parser.add_argument('-fake', '--fake_hyp', required=False, action='store_true', help='Use a fake hypothesis for testing')
parser.add_argument('-limit', '--limit', required=False, default=None,type= int, help = 'Limit to X number of audio files')
nlp_model = NLPModel()
io_handler = IOHandler()
nlp_options = NLPOptions()
configuration = Configuration()
# Turn on punctuation .. why not.. no bearing on WER
configuration.set_enableAutomaticPunctuation(True)
args = parser.parse_args()
limit = args.limit
cloud_store_uri = args.cloud_store_uri
io_handler.set_result_path(args.local_results_path)
only_transcribe = args.transcriptions_only
nlp_model.set_n2w(args.numbers_to_words)
nlp_model.set_apply_stemming(args.stem)
nlp_model.set_remove_stop_words(args.remove_stop_words)
nlp_model.set_expand_contractions(args.expand)
class NLPOptions(object):
nlp_model = NLPModel()
contractions = None
def __init__(self):
from utilities.contractions import contractions_dictionary
self.contractions = contractions_dictionary
def expand_contractions(self, text):
import re
contractions = self.contractions
contractions_pattern = re.compile('({})'.format('|'.join(
contractions.keys())),
flags=re.IGNORECASE | re.DOTALL)
def expand_match(contraction):
match = contraction.group(0)
first_char = match[0]
expanded_contraction = contractions.get(match) \
if contractions.get(match) \
else contractions.get(match.lower())
expanded_contraction = first_char + expanded_contraction[1:]
# Hack for this bug: https://github.com/dipanjanS/practical-machine-learning-with-python/issues/24
if expanded_contraction == "as not":
return "is not"
return expanded_contraction
expanded_text = contractions_pattern.sub(expand_match, text)
expanded_text = re.sub("'", "", expanded_text)
return expanded_text
def convert_numbers_to_words(self, text):
# does not handle things like 21st, 4th
from nltk.tokenize import word_tokenize
import inflect
result = ''
i = inflect.engine()
word_tokens = word_tokenize(text)
for w in word_tokens:
if w.isdigit():
numword = i.number_to_words(w)
result += f' {numword}'
else:
result += f' {w}'
return result
def remove_stop_words(self, text):
from nltk.corpus import stopwords
import string
result = str()
stop_words = set(stopwords.words('english'))
words = text.split()
table = str.maketrans('', '', string.punctuation)
stripped = [w.translate(table) for w in words]
filtered = [w for w in stripped if not w in stop_words]
for w in filtered:
result += " " + w
return result
def apply_stemming(self, text):
from nltk.stem import PorterStemmer
from nltk.tokenize import word_tokenize
results = ""
ps = PorterStemmer()
words = word_tokenize(text)
for w in words:
results += (ps.stem(w) + " ")
return results
def apply_nlp_options(self, nlp_model, hyp):
stem = nlp_model.get_apply_stemming()
stop = nlp_model.get_remove_stop_words()
n2w = nlp_model.get_n2w()
exp = nlp_model.get_expand_contractions()
if stem and not stop and not n2w and not exp:
return self.apply_stemming(hyp)
elif not stem and stop and not n2w and not exp:
return self.remove_stop_words(hyp)
elif not stem and not stop and n2w and not exp:
return self.convert_numbers_to_words(hyp)
elif not stem and not stop and not n2w and exp:
return self.expand_contractions(hyp)
elif stem and stop and not n2w and not exp:
step_one = self.remove_stop_words(hyp)
return self.apply_stemming(step_one)
elif stem and not stop and n2w and not exp:
step_one = self.convert_numbers_to_words(hyp)
return self.apply_stemming(step_one)
elif stem and not stop and not n2w and exp:
step_one = self.expand_contractions(hyp)
return self.apply_stemming(step_one)
elif not stem and stop and n2w and not exp:
step_one = self.convert_numbers_to_words(hyp)
return self.remove_stop_words(step_one)
elif not stem and not stop and n2w and exp:
step_one = self.expand_contractions(hyp)
return self.convert_numbers_to_words(step_one)
elif not stem and stop and n2w and exp:
step_one = self.expand_contractions(hyp)
step_two = self.convert_numbers_to_words(step_one)
return self.remove_stop_words(step_two)
elif stem and not stop and n2w and exp:
step_one = self.expand_contractions(hyp)
step_two = self.convert_numbers_to_words(step_one)
return self.apply_stemming(step_two)
elif stem and stop and n2w and not exp:
step_one = self.convert_numbers_to_words(hyp)
step_two = self.remove_stop_words(step_one)
return self.apply_stemming(step_two)
elif stem and stop and not n2w and exp:
step_one = self.expand_contractions(hyp)
step_two = self.remove_stop_words(step_one)
return self.apply_stemming(step_two)
elif stem and stop and n2w and not exp:
step_one = self.convert_numbers_to_words(hyp)
step_two = self.remove_stop_words(step_one)
return self.apply_stemming(step_two)
elif stem and stop and n2w and exp:
step_one = self.expand_contractions(hyp)
step_two = self.convert_numbers_to_words(step_one)
step_three = self.remove_stop_words(step_two)
return self.apply_stemming(step_three)
