def classifyLexical():
assert request.method == 'POST'
text_file = request.form['textfile']
if not text_file:
text = request.form['text']
else:
file_name = os.path.join(route_folder, TEXT_DATA, text_file)
inputTextReader = InputTextReader()
text = inputTextReader.readFile(file_name)
# predict lexical
load_config(LEXICAL_MODEL_FOLDER, request.form['lexical_folder'])
input_text = InputText(text)
punctuations_probs = lexical_classifier.predict(input_text)
(window_size, punctuation_pos, pos_tagging) = lexical_classifier.get_lexical_parameter()
question_mark = sbd.config.getboolean('features', 'use_question_mark')
classes = get_lexical_classes(question_mark)
all_probs = convert_probabilities(len(input_text.tokens), punctuation_pos, punctuations_probs, classes)
jsonConverter = JsonConverter(punctuation_pos, window_size, None, None, pos_tagging)
data = jsonConverter.convert_lexical(input_text.tokens, all_probs)
if not text_file:
text_file = "custom_input"
file_name = os.path.join(route_folder, TEXT_DATA, text_file + ".result")
resultWriter = ResultWriter(classes)
resultWriter.writeToFile(file_name, input_text.tokens, all_probs)
return json.dumps(data)
def classifyAudioLexical():
assert request.method == 'POST'
# get example folder
example_folder = os.path.join(route_folder, AUDIO_EXAMPLE_FOLDER, request.form['example'])
ctm_file, pitch_file, energy_file = get_audio_files(example_folder)
# parse ctm_file, pitch_file and energy_file
parser = AudioParser()
talks = parser.parse(ctm_file)
# predict audio
load_config(AUDIO_MODEL_FOLDER, request.form['audio_folder'])
audio_probs = audio_classifier.predict(InputAudio(talks))
# predict lexical
load_config(LEXICAL_MODEL_FOLDER, request.form['lexical_folder'])
input_text = InputText(talks)
lexical_probs = lexical_classifier.predict(input_text)
# get config parameter
(lexical_window_size, lexical_punctuation_pos, pos_tagging) = lexical_classifier.get_lexical_parameter()
(audio_window_size, audio_punctuation_pos) = audio_classifier.get_audio_parameter()
# write audio results
audio_classes = ["NONE", "PERIOD"]
all_audio_probs = convert_probabilities(len(input_text.tokens), audio_punctuation_pos, audio_probs, audio_classes)
file_name = os.path.join(route_folder, AUDIO_EXAMPLE_FOLDER, request.form['example'] + ".result")
resultWriter = ResultWriter(audio_classes)
resultWriter.writeToFile(file_name, input_text.tokens, all_audio_probs)
# fusion
fusion = ThresholdFusion()
fusion.init_parameters(lexical_punctuation_pos, lexical_window_size, audio_punctuation_pos, audio_window_size)
fusion_probs = fusion.fuse(len(input_text.tokens), lexical_probs, audio_probs)
# convert it into json
jsonConverter = JsonConverter(lexical_punctuation_pos, lexical_window_size, audio_punctuation_pos, audio_window_size, pos_tagging)
data = jsonConverter.convert_fusion(input_text.tokens, fusion_probs, lexical_probs, audio_probs)
return json.dumps(data)
