1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
|
%global _empty_manifest_terminate_build 0
Name: python-phonemizer
Version: 3.2.1
Release: 1
Summary: Simple text to phones converter for multiple languages
License: GPL3
URL: https://github.com/bootphon/phonemizer
Source0: https://mirrors.nju.edu.cn/pypi/web/packages/2f/23/090873aa616dfaf9209dc319841204e0e85b3ff6ca6032551216e3dfe153/phonemizer-3.2.1.tar.gz
BuildArch: noarch
Requires: python3-joblib
Requires: python3-segments
Requires: python3-attrs
Requires: python3-dlinfo
Requires: python3-typing-extensions
Requires: python3-sphinx
Requires: python3-sphinx-rtd-theme
Requires: python3-pytest
%description
# Phonemizer -- *foʊnmaɪzɚ*
* The phonemizer allows simple phonemization of words and texts in many languages.
* Provides both the `phonemize` command-line tool and the Python function
`phonemizer.phonemize`. See [the package's documentation](https://bootphon.github.io/phonemizer/).
* It is based on four backends: **espeak**, **espeak-mbrola**, **festival** and
**segments**. The backends have different properties and capabilities resumed
in table below. The backend choice is let to the user.
* [espeak-ng](https://github.com/espeak-ng/espeak-ng) is a Text-to-Speech
software supporting a lot of languages and IPA (International Phonetic
Alphabet) output.
* [espeak-ng-mbrola](https://github.com/espeak-ng/espeak-ng/blob/master/docs/mbrola.md)
uses the SAMPA phonetic alphabet instead of IPA but does not preserve word
boundaries.
* [festival](http://www.cstr.ed.ac.uk/projects/festival) is another
Tex-to-Speech engine. Its phonemizer backend currently supports only
American English. It uses a [custom phoneset][festival-phoneset], but it
allows tokenization at the syllable level.
* [segments](https://github.com/cldf/segments) is a Unicode tokenizer that
build a phonemization from a grapheme to phoneme mapping provided as a file
by the user.
| | espeak | espeak-mbrola | festival | segments |
| ---: | --- | --- | --- | --- |
| **phone set** | [IPA] | [SAMPA] | [custom][festival-phoneset] | user defined |
| **supported languages** | [100+][espeak-languages] | [35][mbrola-languages] | US English | user defined |
| **processing speed** | fast | slow | very slow | fast |
| **phone tokens** | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: |
| **syllable tokens** | :x: | :x: | :heavy_check_mark: | :x: |
| **word tokens** | :heavy_check_mark: | :x: | :heavy_check_mark: | :heavy_check_mark: |
| **punctuation preservation** | :heavy_check_mark: | :x: | :heavy_check_mark: | :heavy_check_mark: |
| **stressed phones** | :heavy_check_mark: | :x: | :x: | :x: |
| [**tie**][tie-IPA] | :heavy_check_mark: | :x: | :x: | :x: |
## Citation
To refenrece the `phonemizer` in your own work, please cite the following [JOSS
paper](https://joss.theoj.org/papers/10.21105/joss.03958).
```bibtex
@article{Bernard2021,
doi = {10.21105/joss.03958},
url = {https://doi.org/10.21105/joss.03958},
year = {2021},
publisher = {The Open Journal},
volume = {6},
number = {68},
pages = {3958},
author = {Mathieu Bernard and Hadrien Titeux},
title = {Phonemizer: Text to Phones Transcription for Multiple Languages in Python},
journal = {Journal of Open Source Software}
}
```
## Licence
**Copyright 2015-2021 Mathieu Bernard**
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
[badge-test-linux]: https://github.com/bootphon/phonemizer/actions/workflows/linux.yaml/badge.svg?branch=master
[badge-test-macos]: https://github.com/bootphon/phonemizer/actions/workflows/macos.yaml/badge.svg?branch=master
[badge-test-windows]: https://github.com/bootphon/phonemizer/actions/workflows/windows.yaml/badge.svg?branch=master
[badge-codecov]: https://img.shields.io/codecov/c/github/bootphon/phonemizer
[badge-github-version]: https://img.shields.io/github/v/release/bootphon/phonemizer
[badge-pypi-version]: https://img.shields.io/pypi/v/phonemizer
[badge-pypi-downloads]: https://img.shields.io/pypi/dm/phonemizer
[badge-joss]: https://joss.theoj.org/papers/08d1ffc14f233f56942f78f3742b266e/status.svg
[badge-zenodo]: https://zenodo.org/badge/56728069.svg
[phonemizer-1.0]: https://github.com/bootphon/phonemizer/releases/tag/v1.0
[festival-phoneset]: http://www.festvox.org/bsv/c4711.html
[IPA]: https://en.wikipedia.org/wiki/International_Phonetic_Alphabet
[SAMPA]: https://en.wikipedia.org/wiki/SAMPA
[phonemize-function]: https://github.com/bootphon/phonemizer/blob/c5e2f3878d6db391ec7253173f44e4a85cfe41e3/phonemizer/phonemize.py#L33-L156
[tie-IPA]: https://en.wikipedia.org/wiki/Tie_(typography)#International_Phonetic_Alphabet
[espeak-languages]: https://github.com/espeak-ng/espeak-ng/blob/master/docs/languages.md
[mbrola-languages]: https://github.com/numediart/MBROLA-voices
%package -n python3-phonemizer
Summary: Simple text to phones converter for multiple languages
Provides: python-phonemizer
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-phonemizer
# Phonemizer -- *foʊnmaɪzɚ*
* The phonemizer allows simple phonemization of words and texts in many languages.
* Provides both the `phonemize` command-line tool and the Python function
`phonemizer.phonemize`. See [the package's documentation](https://bootphon.github.io/phonemizer/).
* It is based on four backends: **espeak**, **espeak-mbrola**, **festival** and
**segments**. The backends have different properties and capabilities resumed
in table below. The backend choice is let to the user.
* [espeak-ng](https://github.com/espeak-ng/espeak-ng) is a Text-to-Speech
software supporting a lot of languages and IPA (International Phonetic
Alphabet) output.
* [espeak-ng-mbrola](https://github.com/espeak-ng/espeak-ng/blob/master/docs/mbrola.md)
uses the SAMPA phonetic alphabet instead of IPA but does not preserve word
boundaries.
* [festival](http://www.cstr.ed.ac.uk/projects/festival) is another
Tex-to-Speech engine. Its phonemizer backend currently supports only
American English. It uses a [custom phoneset][festival-phoneset], but it
allows tokenization at the syllable level.
* [segments](https://github.com/cldf/segments) is a Unicode tokenizer that
build a phonemization from a grapheme to phoneme mapping provided as a file
by the user.
| | espeak | espeak-mbrola | festival | segments |
| ---: | --- | --- | --- | --- |
| **phone set** | [IPA] | [SAMPA] | [custom][festival-phoneset] | user defined |
| **supported languages** | [100+][espeak-languages] | [35][mbrola-languages] | US English | user defined |
| **processing speed** | fast | slow | very slow | fast |
| **phone tokens** | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: |
| **syllable tokens** | :x: | :x: | :heavy_check_mark: | :x: |
| **word tokens** | :heavy_check_mark: | :x: | :heavy_check_mark: | :heavy_check_mark: |
| **punctuation preservation** | :heavy_check_mark: | :x: | :heavy_check_mark: | :heavy_check_mark: |
| **stressed phones** | :heavy_check_mark: | :x: | :x: | :x: |
| [**tie**][tie-IPA] | :heavy_check_mark: | :x: | :x: | :x: |
## Citation
To refenrece the `phonemizer` in your own work, please cite the following [JOSS
paper](https://joss.theoj.org/papers/10.21105/joss.03958).
```bibtex
@article{Bernard2021,
doi = {10.21105/joss.03958},
url = {https://doi.org/10.21105/joss.03958},
year = {2021},
publisher = {The Open Journal},
volume = {6},
number = {68},
pages = {3958},
author = {Mathieu Bernard and Hadrien Titeux},
title = {Phonemizer: Text to Phones Transcription for Multiple Languages in Python},
journal = {Journal of Open Source Software}
}
```
## Licence
**Copyright 2015-2021 Mathieu Bernard**
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
[badge-test-linux]: https://github.com/bootphon/phonemizer/actions/workflows/linux.yaml/badge.svg?branch=master
[badge-test-macos]: https://github.com/bootphon/phonemizer/actions/workflows/macos.yaml/badge.svg?branch=master
[badge-test-windows]: https://github.com/bootphon/phonemizer/actions/workflows/windows.yaml/badge.svg?branch=master
[badge-codecov]: https://img.shields.io/codecov/c/github/bootphon/phonemizer
[badge-github-version]: https://img.shields.io/github/v/release/bootphon/phonemizer
[badge-pypi-version]: https://img.shields.io/pypi/v/phonemizer
[badge-pypi-downloads]: https://img.shields.io/pypi/dm/phonemizer
[badge-joss]: https://joss.theoj.org/papers/08d1ffc14f233f56942f78f3742b266e/status.svg
[badge-zenodo]: https://zenodo.org/badge/56728069.svg
[phonemizer-1.0]: https://github.com/bootphon/phonemizer/releases/tag/v1.0
[festival-phoneset]: http://www.festvox.org/bsv/c4711.html
[IPA]: https://en.wikipedia.org/wiki/International_Phonetic_Alphabet
[SAMPA]: https://en.wikipedia.org/wiki/SAMPA
[phonemize-function]: https://github.com/bootphon/phonemizer/blob/c5e2f3878d6db391ec7253173f44e4a85cfe41e3/phonemizer/phonemize.py#L33-L156
[tie-IPA]: https://en.wikipedia.org/wiki/Tie_(typography)#International_Phonetic_Alphabet
[espeak-languages]: https://github.com/espeak-ng/espeak-ng/blob/master/docs/languages.md
[mbrola-languages]: https://github.com/numediart/MBROLA-voices
%package help
Summary: Development documents and examples for phonemizer
Provides: python3-phonemizer-doc
%description help
# Phonemizer -- *foʊnmaɪzɚ*
* The phonemizer allows simple phonemization of words and texts in many languages.
* Provides both the `phonemize` command-line tool and the Python function
`phonemizer.phonemize`. See [the package's documentation](https://bootphon.github.io/phonemizer/).
* It is based on four backends: **espeak**, **espeak-mbrola**, **festival** and
**segments**. The backends have different properties and capabilities resumed
in table below. The backend choice is let to the user.
* [espeak-ng](https://github.com/espeak-ng/espeak-ng) is a Text-to-Speech
software supporting a lot of languages and IPA (International Phonetic
Alphabet) output.
* [espeak-ng-mbrola](https://github.com/espeak-ng/espeak-ng/blob/master/docs/mbrola.md)
uses the SAMPA phonetic alphabet instead of IPA but does not preserve word
boundaries.
* [festival](http://www.cstr.ed.ac.uk/projects/festival) is another
Tex-to-Speech engine. Its phonemizer backend currently supports only
American English. It uses a [custom phoneset][festival-phoneset], but it
allows tokenization at the syllable level.
* [segments](https://github.com/cldf/segments) is a Unicode tokenizer that
build a phonemization from a grapheme to phoneme mapping provided as a file
by the user.
| | espeak | espeak-mbrola | festival | segments |
| ---: | --- | --- | --- | --- |
| **phone set** | [IPA] | [SAMPA] | [custom][festival-phoneset] | user defined |
| **supported languages** | [100+][espeak-languages] | [35][mbrola-languages] | US English | user defined |
| **processing speed** | fast | slow | very slow | fast |
| **phone tokens** | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: |
| **syllable tokens** | :x: | :x: | :heavy_check_mark: | :x: |
| **word tokens** | :heavy_check_mark: | :x: | :heavy_check_mark: | :heavy_check_mark: |
| **punctuation preservation** | :heavy_check_mark: | :x: | :heavy_check_mark: | :heavy_check_mark: |
| **stressed phones** | :heavy_check_mark: | :x: | :x: | :x: |
| [**tie**][tie-IPA] | :heavy_check_mark: | :x: | :x: | :x: |
## Citation
To refenrece the `phonemizer` in your own work, please cite the following [JOSS
paper](https://joss.theoj.org/papers/10.21105/joss.03958).
```bibtex
@article{Bernard2021,
doi = {10.21105/joss.03958},
url = {https://doi.org/10.21105/joss.03958},
year = {2021},
publisher = {The Open Journal},
volume = {6},
number = {68},
pages = {3958},
author = {Mathieu Bernard and Hadrien Titeux},
title = {Phonemizer: Text to Phones Transcription for Multiple Languages in Python},
journal = {Journal of Open Source Software}
}
```
## Licence
**Copyright 2015-2021 Mathieu Bernard**
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
[badge-test-linux]: https://github.com/bootphon/phonemizer/actions/workflows/linux.yaml/badge.svg?branch=master
[badge-test-macos]: https://github.com/bootphon/phonemizer/actions/workflows/macos.yaml/badge.svg?branch=master
[badge-test-windows]: https://github.com/bootphon/phonemizer/actions/workflows/windows.yaml/badge.svg?branch=master
[badge-codecov]: https://img.shields.io/codecov/c/github/bootphon/phonemizer
[badge-github-version]: https://img.shields.io/github/v/release/bootphon/phonemizer
[badge-pypi-version]: https://img.shields.io/pypi/v/phonemizer
[badge-pypi-downloads]: https://img.shields.io/pypi/dm/phonemizer
[badge-joss]: https://joss.theoj.org/papers/08d1ffc14f233f56942f78f3742b266e/status.svg
[badge-zenodo]: https://zenodo.org/badge/56728069.svg
[phonemizer-1.0]: https://github.com/bootphon/phonemizer/releases/tag/v1.0
[festival-phoneset]: http://www.festvox.org/bsv/c4711.html
[IPA]: https://en.wikipedia.org/wiki/International_Phonetic_Alphabet
[SAMPA]: https://en.wikipedia.org/wiki/SAMPA
[phonemize-function]: https://github.com/bootphon/phonemizer/blob/c5e2f3878d6db391ec7253173f44e4a85cfe41e3/phonemizer/phonemize.py#L33-L156
[tie-IPA]: https://en.wikipedia.org/wiki/Tie_(typography)#International_Phonetic_Alphabet
[espeak-languages]: https://github.com/espeak-ng/espeak-ng/blob/master/docs/languages.md
[mbrola-languages]: https://github.com/numediart/MBROLA-voices
%prep
%autosetup -n phonemizer-3.2.1
%build
%py3_build
%install
%py3_install
install -d -m755 %{buildroot}/%{_pkgdocdir}
if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi
if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi
if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi
if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi
pushd %{buildroot}
if [ -d usr/lib ]; then
find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/lib64 ]; then
find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/bin ]; then
find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/sbin ]; then
find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst
fi
touch doclist.lst
if [ -d usr/share/man ]; then
find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst
fi
popd
mv %{buildroot}/filelist.lst .
mv %{buildroot}/doclist.lst .
%files -n python3-phonemizer -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Fri May 05 2023 Python_Bot <Python_Bot@openeuler.org> - 3.2.1-1
- Package Spec generated
|
