fix the bug there are characters in the lexicon which cannot be described in ascii.

This commit is contained in:
yemaozi88 2019-02-03 00:34:35 +01:00
parent dc6b7b84b6
commit 22cccfb61d
9 changed files with 199 additions and 103 deletions

Binary file not shown.

View File

@ -4,8 +4,7 @@
<SchemaVersion>2.0</SchemaVersion>
<ProjectGuid>4d8c8573-32f0-4a62-9e62-3ce5cc680390</ProjectGuid>
<ProjectHome>.</ProjectHome>
<StartupFile>
</StartupFile>
<StartupFile>fame_hmm.py</StartupFile>
<SearchPath>
</SearchPath>
<WorkingDirectory>.</WorkingDirectory>

View File

@ -39,11 +39,11 @@ toolbox_dir = os.path.join(repo_dir, 'toolbox')
#config_hvite = os.path.join(htk_config_dir, 'config.HVite')
#acoustic_model = os.path.join(htk_config_dir, 'hmmdefs.compo')
#acoustic_model = r'c:\cygwin64\home\A.Kunikoshi\acoustic_model\model\barbara\hmm128-2\hmmdefs.compo'
#phonelist_txt = os.path.join(htk_config_dir, 'phonelist.txt')
phonelist_txt = os.path.join(htk_dir, 'config', 'phonelist.txt')
WSL_dir = r'C:\OneDrive\WSL'
#fame_dir = os.path.join(WSL_dir, 'kaldi-trunk', 'egs', 'fame')
fame_dir = r'd:\_corpus\fame'
fame_dir = r'c:\OneDrive\Research\rug\_data\FAME'
fame_s5_dir = os.path.join(fame_dir, 's5')
fame_corpus_dir = os.path.join(fame_dir, 'corpus')

View File

@ -290,15 +290,17 @@ def lexicon_asr2htk(lexicon_file_asr, lexicon_file_htk):
"""
lex_asr = load_lexicon(lexicon_file_asr)
def word2htk_(row):
return word2htk(row['word'])
def asr2htk_space_delimited_(row):
return asr2htk_space_delimited(row['pronunciation'])
lex_htk = pd.DataFrame({
'word': lex_asr['word'],
'word': lex_asr.apply(word2htk_, axis=1).str.upper(),
'pronunciation': lex_asr.apply(asr2htk_space_delimited_, axis=1)
})
lex_htk = lex_htk.ix[:, ['word', 'pronunciation']]
lex_htk.to_csv(lexicon_file_htk, header=None, index=None, sep='\t')
lex_htk.to_csv(lexicon_file_htk, header=None, index=None, sep='\t', encoding='utf-8')
return
@ -316,20 +318,26 @@ def combine_lexicon(lexicon_file1, lexicon_file2, lexicon_out):
lex2 = load_lexicon(lexicon_file2)
lex = pd.concat([lex1, lex2])
lex = lex.sort_values(by='word', ascending=True)
lex.to_csv(lexicon_out, index=False, header=False, encoding="utf-8", sep='\t')
lex.to_csv(lexicon_out, index=False, header=False, sep='\t', encoding='utf-8')
def fix_single_quote(lexicon_file):
""" add '\' before all single quote at the beginning of words.
convert special characters to ascii compatible characters.
Args:
lexicon_file (path): lexicon file, which will be overwitten.
"""
lex = load_lexicon(lexicon_file)
lex = lex.dropna() # remove N/A.
for i in lex[lex['word'].str.startswith('\'')].index.values:
lex.iat[i, 0] = lex.iat[i, 0].replace('\'', '\\\'')
# to_csv does not work with space seperator. therefore all tabs should manually be replaced.
#lex.to_csv(lexicon_file, index=False, header=False, encoding="utf-8", sep=' ', quoting=csv.QUOTE_NONE, escapechar='\\')
lex.to_csv(lexicon_file, index=False, header=False, encoding="utf-8", sep='\t')
lex.to_csv(lexicon_file, index=False, header=False, sep='\t', encoding='utf-8')
return
def word2htk(word):
return ''.join([fame_asr.translation_key_word2htk.get(i, i) for i in word])

View File

@ -3,6 +3,7 @@ import os
os.chdir(r'C:\Users\Aki\source\repos\acoustic_model\acoustic_model')
import tempfile
import shutil
#import configparser
#import subprocess
import time
@ -11,6 +12,7 @@ import numpy as np
import pandas as pd
import fame_functions
from phoneset import fame_ipa, fame_asr
import defaultfiles as default
sys.path.append(default.toolbox_dir)
import file_handling as fh
@ -28,7 +30,7 @@ dataset_list = ['devel', 'test', 'train']
# procedure
extract_features = 0
make_lexicon = 0
make_lexicon = 1
make_mlf = 0
combine_files = 0
flat_start = 0
@ -44,6 +46,9 @@ lexicon_htk_asr = os.path.join(default.htk_dir, 'lexicon', 'lex.htk_asr')
lexicon_htk_oov = os.path.join(default.htk_dir, 'lexicon', 'lex.htk_oov')
lexicon_htk = os.path.join(default.htk_dir, 'lexicon', 'lex.htk')
global_ded = os.path.join(default.htk_dir, 'config', 'global.ded')
#hcompv_scp = output_dir + '\\scp\\combined.scp'
#combined_mlf = output_dir + '\\label\\combined.mlf'
@ -60,14 +65,17 @@ if not os.path.exists(feature_dir):
tmp_dir = os.path.join(default.htk_dir, 'tmp')
if not os.path.exists(tmp_dir):
os.makedirs(tmp_dir)
label_dir = os.path.join(default.htk_dir, 'label')
if not os.path.exists(label_dir):
os.makedirs(label_dir)
## ======================= extract features =======================
if extract_features:
print('==== extract features ====\n')
for dataset in dataset_list:
print('==== dataset: {} ===='.format(dataset))
print('==== extract features on dataset {} ====\n'.format(dataset))
# a script file for HCopy
print(">>> making a script file for HCopy... \n")
@ -89,6 +97,8 @@ if extract_features:
hcompv_scp = os.path.join(tmp_dir, dataset + '.scp')
fh.make_filelist(feature_dir_, hcompv_scp, '.mfc')
os.remove(hcopy_scp.name)
## ======================= make lexicon for HTK =======================
if make_lexicon:
@ -114,94 +124,132 @@ if make_lexicon:
fame_functions.fix_single_quote(lexicon_htk)
## ======================= make phonelist =======================
#phonelist_txt = os.path.join(default.htk_dir, 'config', 'phonelist.txt')
#pyhtk.create_phonelist_file(fame_asr.phoneset_htk, phonelist_txt)
#sentence = 'ien fan de minsken fan it deiferbliuw sels brúntsje visser'
#log_txt = os.path.join(default.htk_dir, 'config', 'log.txt')
#dictionary_file = os.path.join(default.htk_dir, 'config', 'test.dic')
#pyhtk.create_dictionary(
# sentence, global_ded, log_txt, dictionary_file, lexicon_htk)
#pyhtk.create_dictionary_without_log(
# sentence, global_ded, dictionary_file, lexicon_htk)
## ======================= make label file =======================
if make_mlf:
print("==== make mlf ====\n")
print("generating word level transcription...\n")
for dataset in dataset_list:
hcompv_scp = output_dir + '\\scp\\' + dataset + '.scp'
hcompv_scp2 = output_dir + '\\scp\\' + dataset + '_all_words_in_lexicon.scp'
script_list = FAME_dir + '\\data\\' + dataset + '\\text'
mlf_word = output_dir + '\\label\\' + dataset + '_word.mlf'
mlf_phone = output_dir + '\\label\\' + dataset + '_phone.mlf'
timer_start = time.time()
print("==== generating word level transcription on dataset {}\n".format(dataset))
# lexicon
lexicon_htk = pd.read_table(lex_htk, names=['word', 'pronunciation'])
# list of features
with open(hcompv_scp) as fin:
features = fin.read()
features = features.split('\n')
#hcompv_scp = output_dir + '\\scp\\' + dataset + '.scp'
#hcompv_scp2 = output_dir + '\\scp\\' + dataset + '_all_words_in_lexicon.scp'
script_list = os.path.join(default.fame_dir, 'data', dataset, 'text')
#mlf_word = output_dir + '\\label\\' + dataset + '_word.mlf'
#mlf_phone = output_dir + '\\label\\' + dataset + '_phone.mlf'
wav_dir = os.path.join(default.fame_dir, 'fame', 'wav', dataset)
dictionary_file = os.path.join(wav_dir, 'temp.dic')
# list of scripts
with open(script_list, "rt", encoding="utf-8") as fin:
scripts = fin.read()
scripts = pd.Series(scripts.split('\n'))
scripts = fin.read().split('\n')
i = 0
missing_words = []
fscp = open(hcompv_scp2, 'wt')
fmlf = open(mlf_word, "wt", encoding="utf-8")
fmlf.write("#!MLF!#\n")
feature_nr = 1
for feature in features:
sys.stdout.write("\r%d/%d" % (feature_nr, len(features)))
sys.stdout.flush()
feature_nr += 1
file_basename = os.path.basename(feature).replace('.mfc', '')
for line in scripts:
#for line in ['sp0035m_train_1975_fragmentenvraaggesprekkenruilverkaveling_15413 en dat kan men nog meer']:
# sample line:
# sp0457m_test_1968_plakkenfryslanterhorne_2168 en dan begjinne je natuerlik
filename_ = line.split(' ')[0]
filename = '_'.join(filename_.split('_')[1:])
sentence = ' '.join(line.split(' ')[1:])
# get words from scripts.
wav_file = os.path.join(wav_dir, filename + '.wav')
if len(re.findall(r'[\w]+[âêûô\'ú]+[\w]+', sentence))==0:
try:
script = scripts[scripts.str.contains(file_basename)]
except IndexError:
script = []
sentence_ascii = bytes(sentence, 'ascii')
except UnicodeEncodeError:
print(sentence)
#if os.path.exists(wav_file):
# #dictionary_file = os.path.join(wav_dir, filename + '.dic')
# if pyhtk.create_dictionary_without_log(
# sentence, global_ded, dictionary_file, lexicon_htk) == 0:
# # when the file name is too long, HDMan command does not work.
# # therefore first temporary dictionary_file is made, then renamed.
# shutil.move(dictionary_file, os.path.join(wav_dir, filename + '.dic'))
# label_file = os.path.join(wav_dir, filename + '.lab')
# pyhtk.create_label_file(sentence, label_file)
# else:
# os.remove(dictionary_file)
print("elapsed time: {}".format(time.time() - timer_start))
# lexicon
#lexicon_htk = pd.read_table(lex_htk, names=['word', 'pronunciation'])
if len(script) != 0:
script_id = script.index[0]
script_txt = script.get(script_id)
script_words = script_txt.split(' ')
del script_words[0]
# list of features
#with open(hcompv_scp) as fin:
# features = fin.read()
# features = features.split('\n')
#i = 0
#missing_words = []
#fscp = open(hcompv_scp2, 'wt')
#fmlf = open(mlf_word, "wt", encoding="utf-8")
#fmlf.write("#!MLF!#\n")
#feature_nr = 1
#for feature in features:
# sys.stdout.write("\r%d/%d" % (feature_nr, len(features)))
# sys.stdout.flush()
# feature_nr += 1
# file_basename = os.path.basename(feature).replace('.mfc', '')
# # get words from scripts.
# try:
# script = scripts[scripts.str.contains(file_basename)]
# except IndexError:
# script = []
# if len(script) != 0:
# script_id = script.index[0]
# script_txt = script.get(script_id)
# script_words = script_txt.split(' ')
# del script_words[0]
# check if all words can be found in the lexicon.
SCRIPT_WORDS = []
script_prons = []
is_in_lexicon = 1
for word in script_words:
WORD = word.upper()
SCRIPT_WORDS.append(WORD)
extracted = lexicon_htk[lexicon_htk['word']==WORD]
if len(extracted) == 0:
missing_words.append(word)
script_prons.append(extracted)
is_in_lexicon *= len(extracted)
# SCRIPT_WORDS = []
# script_prons = []
# is_in_lexicon = 1
# for word in script_words:
# WORD = word.upper()
# SCRIPT_WORDS.append(WORD)
# extracted = lexicon_htk[lexicon_htk['word']==WORD]
# if len(extracted) == 0:
# missing_words.append(word)
# script_prons.append(extracted)
# is_in_lexicon *= len(extracted)
# if all pronunciations are found in the lexicon, update scp and mlf files.
if is_in_lexicon:
# if is_in_lexicon:
# add the feature filename into the .scp file.
fscp.write("{}\n".format(feature))
i += 1
# fscp.write("{}\n".format(feature))
# i += 1
# add the words to the mlf file.
fmlf.write('\"*/{}.lab\"\n'.format(file_basename))
# fmlf.write('\"*/{}.lab\"\n'.format(file_basename))
#fmlf.write('{}'.format('\n'.join(SCRIPT_WORDS)))
for word_ in SCRIPT_WORDS:
if word_[0] == '\'':
word_ = '\\' + word_
fmlf.write('{}\n'.format(word_))
fmlf.write('.\n')
print("\n{0} has {1} samples.\n".format(dataset, i))
np.save(output_dir + '\\missing_words' + '_' + dataset + '.npy', missing_words)
# for word_ in SCRIPT_WORDS:
# if word_[0] == '\'':
# word_ = '\\' + word_
# fmlf.write('{}\n'.format(word_))
# fmlf.write('.\n')
# print("\n{0} has {1} samples.\n".format(dataset, i))
# np.save(output_dir + '\\missing_words' + '_' + dataset + '.npy', missing_words)
fscp.close()
fmlf.close()
# fscp.close()
# fmlf.close()
## generate phone level transcription
print("generating phone level transcription...\n")
mkphones = output_dir + '\\label\\mkphones0.txt'
subprocessStr = r"HLEd -l * -d " + lex_htk_ + ' -i ' + mlf_phone + ' ' + mkphones + ' ' + mlf_word
subprocess.call(subprocessStr, shell=True)
# print("generating phone level transcription...\n")
# mkphones = output_dir + '\\label\\mkphones0.txt'
# subprocessStr = r"HLEd -l * -d " + lex_htk_ + ' -i ' + mlf_phone + ' ' + mkphones + ' ' + mlf_word
# subprocess.call(subprocessStr, shell=True)
## ======================= combined scps and mlfs =======================

View File

@ -3,6 +3,7 @@ import os
os.chdir(r'C:\Users\Aki\source\repos\acoustic_model\acoustic_model')
from collections import Counter
import time
import re
import numpy as np
import pandas as pd
@ -82,22 +83,52 @@ np.save(os.path.join('phoneset', 'fame_ipa2asr.npy'), translation_key_ipa2asr)
## check if all the phones in lexicon.htk are in fame_asr.py.
#timer_start = time.time()
#phoneset_htk = fame_asr.phoneset_htk
#phoneset_lex = fame_functions.get_phoneset_from_lexicon(lexicon_htk)
#phoneset_lex.remove('')
#print("phones which is in lexicon.htk but not in the fame_asr.py are:\n{}".format(
# set(phoneset_htk) - set(phoneset_lex)))
#print("elapsed time: {}".format(time.time() - timer_start))
## statistics over the lexicon
#lex_htk = fame_functions.load_lexicon(lexicon_htk)
#phones_all = (' '.join(lex_htk['pronunciation'])).split(' ')
#c = Counter(phones_all)
#lexicon_out = r'c:\OneDrive\Research\rug\experiments\acoustic_model\fame\htk\lexicon\lex.htk2'
#for i in lex_htk[lex_htk['word'].str.startswith('\'')].index.values:
# lex_htk.iat[i, 0] = lex_htk.iat[i, 0].replace('\'', '\\\'')
## to_csv does not work with space seperator. therefore all tabs should manually be replaced.
##lex_htk.to_csv(lexicon_out, index=False, header=False, encoding="utf-8", sep=' ', quoting=csv.QUOTE_NONE, escapechar='\\')
#lex_htk.to_csv(lexicon_out, index=False, header=False, encoding="utf-8", sep='\t')
## check which letters are not coded in ascii.
print('asr phones which cannot be coded in ascii:\n')
for i in fame_asr.phoneset_short:
try:
i_encoded = i.encode("ascii")
#print("{0} --> {1}".format(i, i.encode("ascii")))
except UnicodeEncodeError:
print(">>> {}".format(i))
print("letters in the scripts which is not coded in ascii:\n")
for dataset in ['train', 'devel', 'test']:
timer_start = time.time()
phoneset_htk = fame_asr.phoneset_htk
phoneset_lex = fame_functions.get_phoneset_from_lexicon(lexicon_htk)
phoneset_lex.remove('')
print("phones which is in lexicon.htk but not in the fame_asr.py are:\n{}".format(
set(phoneset_htk) - set(phoneset_lex)))
print("elapsed time: {}".format(time.time() - timer_start))
# statistics over the lexicon
lex_htk = fame_functions.load_lexicon(lexicon_htk)
phones_all = (' '.join(lex_htk['pronunciation'])).split(' ')
c = Counter(phones_all)
script_list = os.path.join(default.fame_dir, 'data', dataset, 'text')
with open(script_list, "rt", encoding="utf-8") as fin:
scripts = fin.read().split('\n')
for line in scripts:
sentence = ' '.join(line.split(' ')[1:])
sentence_htk = fame_functions.word2htk(sentence)
#if len(re.findall(r'[âêôûč\'àéèúćäëïöü]', sentence))==0:
try:
sentence_htk = bytes(sentence_htk, 'ascii')
except UnicodeEncodeError:
print(sentence)
print(sentence_htk)
lexicon_out = r'c:\OneDrive\Research\rug\experiments\acoustic_model\fame\htk\lexicon\lex.htk2'
for i in lex_htk[lex_htk['word'].str.startswith('\'')].index.values:
lex_htk.iat[i, 0] = lex_htk.iat[i, 0].replace('\'', '\\\'')
# to_csv does not work with space seperator. therefore all tabs should manually be replaced.
#lex_htk.to_csv(lexicon_out, index=False, header=False, encoding="utf-8", sep=' ', quoting=csv.QUOTE_NONE, escapechar='\\')
lex_htk.to_csv(lexicon_out, index=False, header=False, encoding="utf-8", sep='\t')

View File

@ -103,12 +103,22 @@ translation_key_asr2htk = {
}
phoneset_htk = [translation_key_asr2htk.get(i, i) for i in phoneset_short]
## check
#for i in phoneset_short:
# try:
# print("{0} --> {1}".format(i, i.encode("ascii")))
# except UnicodeEncodeError:
# print(">>> {}".format(i))
#not_in_ascii = [
# '\'',
# 'â', 'ê', 'ô', 'û', 'č',
# 'à', 'í', 'é', 'è', 'ú', 'ć',
# 'ä', 'ë', 'ï', 'ö', 'ü'
#]
translation_key_word2htk = {
'\'': '\\\'',
'í':'i1', 'é':'e1', 'ú':'u1', 'ć':'c1',
'à':'a2', 'è':'e2',
'â':'a3', 'ê':'e3', 'ô':'o3', 'û':'u3',
'č':'c4',
'ä': 'ao', 'ë': 'ee', 'ï': 'ie', 'ö': 'oe', 'ü': 'ue',
}
#[translation_key_word2htk.get(i, i) for i in not_in_ascii]
## the list of multi character phones.

0
acoustic_model/test.txt Normal file
View File