to be sure.

This commit is contained in:
yemaozi88 2018-06-13 07:22:53 +09:00
parent bbed340228
commit a8dbb51d0c
8 changed files with 197 additions and 25 deletions

Binary file not shown.

View File

@ -9,6 +9,7 @@ Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "Solution Items", "Solution
ProjectSection(SolutionItems) = preProject
..\forced_alignment\forced_alignment\__init__.py = ..\forced_alignment\forced_alignment\__init__.py
..\forced_alignment\forced_alignment\convert_phone_set.py = ..\forced_alignment\forced_alignment\convert_phone_set.py
..\ipa-xsama-converter\converter.py = ..\ipa-xsama-converter\converter.py
..\forced_alignment\forced_alignment\defaultfiles.py = ..\forced_alignment\forced_alignment\defaultfiles.py
..\forced_alignment\forced_alignment\forced_alignment.pyproj = ..\forced_alignment\forced_alignment\forced_alignment.pyproj
..\forced_alignment\forced_alignment\htk_dict.py = ..\forced_alignment\forced_alignment\htk_dict.py

View File

@ -313,26 +313,3 @@ if train_model:
subprocessStr = 'HHEd -T 1 -H ' + modelN_dir + '\\' + hmmdefs_name + ' -M ' + modelN_dir_next + ' ' + header_file + ' ' + phonelist
subprocess.call(subprocessStr, shell=True)
### ======================= forced alignment =======================
#if forced_alignment:
# try:
# scripts.run_command([
# 'HVite','-T', '1', '-a', '-C', configHVite,
# '-H', AcousticModel, '-m', '-I',
# mlf_file, '-i', fa_file, '-S',
# script_file, htk_dict_file, filePhoneList
# ])
# except:
# print("\033[91mHVite command failed with these input files:\033[0m")
# print(_debug_show_file('HVite config', configHVite))
# print(_debug_show_file('Accoustic model', AcousticModel))
# print(_debug_show_file('Master Label file', mlf_file))
# print(_debug_show_file('Output', fa_file))
# print(_debug_show_file('Script file', script_file))
# print(_debug_show_file('HTK dictionary', htk_dict_file))
# print(_debug_show_file('Phoneme list', filePhoneList))
# raise
##os.remove(hcopy_scp.name)

View File

@ -4,7 +4,7 @@
<SchemaVersion>2.0</SchemaVersion>
<ProjectGuid>4d8c8573-32f0-4a62-9e62-3ce5cc680390</ProjectGuid>
<ProjectHome>.</ProjectHome>
<StartupFile>acoustic_model.py</StartupFile>
<StartupFile>performance_check.py</StartupFile>
<SearchPath>
</SearchPath>
<WorkingDirectory>.</WorkingDirectory>
@ -25,6 +25,12 @@
<Compile Include="acoustic_model_functions.py">
<SubType>Code</SubType>
</Compile>
<Compile Include="convert_xsampa2ipa.py">
<SubType>Code</SubType>
</Compile>
<Compile Include="performance_check.py">
<SubType>Code</SubType>
</Compile>
</ItemGroup>
<ItemGroup>
<Content Include="config.ini" />

View File

@ -0,0 +1,128 @@
""" Conversion between IPA and Xsampa.
Note: this code is based on ipa-xsama-converter/converter.py.
https://github.com/lingz/ipa-xsama-converter/
"""
import json
import sys
import os
#sys.path.append(ipa_xsampa_converter_dir)
#import converter
def load_converter(source, sink, ipa_xsampa_converter_dir):
"""load the converter.
source and sink are either of "ipa", "xsampa" or "sassc".
"""
choices = ["ipa", "xsampa", "sassc"]
# Validate params
try:
choice1 = choices.index(source)
choice2 = choices.index(sink)
if choice1 == choice2:
print("source and destination format are the same.")
except ValueError:
print("source and destination should be one of [ipa xsampa sassc].")
exit(1)
# Mappings from disk
# some may not be used if source or sink is already IPA
source_to_ipa = {}
ipa_to_sink = {}
ipa_xsampa = []
sassc_ipa = []
# The IPAs that actually occur within SASSC
sassc_active_ipa = {}
script_dir = os.path.dirname(os.path.realpath(__file__))
with open(os.path.join(ipa_xsampa_converter_dir, "ipa_xsampa_map.json"), encoding="utf-8") as f:
ipa_xsampa = json.load(f)
sassc_active = source == "sassc" or sink == "sassc"
if sassc_active:
with open(os.path.join(script_dir, "./sassc_ipa.json")) as f:
sassc_ipa = json.load(f)
for pair in sassc_ipa:
for char in pair[1]:
sassc_active_ipa[char] = 1
if source == "xsampa":
for pair in ipa_xsampa:
source_to_ipa[pair[1]] = pair[0]
elif source == "sassc":
for pair in sassc_ipa:
source_to_ipa[pair[0]] = pair[1]
if sink == "xsampa":
for pair in ipa_xsampa:
ipa_to_sink[pair[0]] = pair[1]
elif sink == "sassc":
for pair in sassc_ipa:
ipa_to_sink[pair[1]] = pair[0]
# Combine them into a single mapping
mapping = {}
if source == "ipa":
mapping = ipa_to_sink
elif sink == "ipa":
mapping = source_to_ipa
else:
for k, ipas in source_to_ipa.iteritems():
map_out = ""
failed = False
for ipa in ipas:
val = ipa_to_sink.get(ipa)
if not val:
failed = True
break
map_out += val
mapping[k] = map_out if not failed else None
return mapping
def conversion(source, sink, mapping, line):
"""
conversion.
Args:
mapping: can be obtained with load_converter().
line: must be seperated, by default the seperator is whitespace.
"""
# Edit this to change the seperator
SEPERATOR = " "
line = line.strip()
output = []
#if sassc_active:
# tokens = line.split(SEPERATOR)
#else:
tokens = line
for token in tokens:
if token.isspace():
output.append(token)
continue
# Remove extraneous chars that IPA does not accept
if sink == "sassc":
cleaned_token = u""
for char in token:
if sassc_active_ipa.get(char):
cleaned_token += char
token = cleaned_token
mapped = mapping.get(token)
if not mapped:
print("WARNING: could not map token ", token, file=sys.stderr)
else:
output.append(mapped)
#if sassc_active:
# output = SEPERATOR.join(output)
#else:
output = "".join(output)
return output

View File

@ -0,0 +1,15 @@
Check the indent:
114: output += "\n"
Specify the encoding when the json file is loaded:
46: with open(os.path.join(script_dir, "ipa_xsampa_map.json")) as f:
--> with open(os.path.join(script_dir, "ipa_xsampa_map.json"), encoding="utf-8") as f:
Because unicode is supported in Python 3.6,
86: line = unicode(line, 'utf-8').strip()
--> line = line.strip()
117:sys.stdout.write(output.encode("utf-8"))
--> sys.stdout.write(output)
Change std input into arguments.
12: if len(sys.argv) != 4:

View File

@ -1,4 +1,49 @@
### ======================= forced alignment =======================
import os
import sys
import csv
import subprocess
import numpy as np
import convert_xsampa2ipa
## ======================= user define =======================
forced_alignment_module = r'C:\Users\Aki\source\repos\forced_alignment'
ipa_xsampa_converter_dir = r'C:\Users\Aki\source\repos\ipa-xsama-converter'
csvfile = r"C:\OneDrive\Research\rug\stimmen\Frisian Variants Picture Task Stimmen.csv"
sys.path.append(forced_alignment_module)
from forced_alignment import convert_phone_set
mapping = convert_xsampa2ipa.load_converter('xsampa', 'ipa', ipa_xsampa_converter_dir)
#word_xsampa = 'e:j@X'
#word_ipa = convert_xsampa2ipa.conversion('xsampa', 'ipa', mapping, word_xsampa)
with open(csvfile, encoding="utf-8") as fin:
lines = csv.reader(fin, delimiter=';', lineterminator="\n", skipinitialspace=True)
next(lines, None) # skip the headers
filenames = []
words = []
pronunciations = []
for line in lines:
if line[1] is not '' and len(line) > 5:
filenames.append(line[0])
words.append(line[1])
word_xsampa = line[3]
word_ipa = convert_xsampa2ipa.conversion('xsampa', 'ipa', mapping, word_xsampa)
word_ipa = word_ipa.replace('ː', ':')
word_famehtk = convert_phone_set.ipa2famehtk(word_ipa)
pronunciations.append(word_famehtk)
phonelist = ' '.join(pronunciations)
np.unique(phonelist.split(' '))
## ======================= forced alignment =======================
#if forced_alignment:
# try:
# scripts.run_command([