MycroftAI
/
mimic2
mirror of https://github.com/MycroftAI/mimic2.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge pull request #1 from MycroftAI/mycroft-changes 

Apache license and remove non Apache-compatible code
pull/2/head
Keith Ito 2018-02-05 16:51:45 -08:00 committed by GitHub
parent 8edcd55b3f e35859d0b0
commit 14960104e5
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
7 changed files with 321 additions and 237 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

214
LICENSE
View File

@ -1,19 +1,201 @@
Copyright (c) 2017 Keith Ito
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
1. Definitions.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

170
README.md
View File

@ -1,168 +1,6 @@
# Tacotron
# mimic2
An implementation of Tacotron speech synthesis in TensorFlow.
This is a fork of [keithito/tacotron](https://github.com/keithito/tacotron)
with changes specific to Mimic 2 applied.
### Audio Samples
* **[Audio Samples](https://keithito.github.io/audio-samples/)** from models trained using this repo.
* The first set was trained for 877K steps on the [LJ Speech Dataset](https://keithito.com/LJ-Speech-Dataset/)
* Speech started to become intelligble around 20K steps.
* Although loss continued to decrease, there wasn't much noticable improvement after ~250K steps.
* The second set was trained by [@MXGray](https://github.com/MXGray) for 140K steps on the [Nancy Corpus](http://www.cstr.ed.ac.uk/projects/blizzard/2011/lessac_blizzard2011/).
## Background
Earlier this year, Google published a paper, [Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model](https://arxiv.org/pdf/1703.10135.pdf),
where they present a neural text-to-speech model that learns to synthesize speech directly from
(text, audio) pairs. However, they didn't release their source code or training data. This is an
attempt to provide an open-source implementation of the model described in their paper.
The quality isn't as good as Google's demo yet, but hopefully it will get there someday :-).
Pull requests are welcome!
## Quick Start
### Installing dependencies
1. Install Python 3.
2. Install the latest version of [TensorFlow](https://www.tensorflow.org/install/) for your platform. For better
performance, install with GPU support if it's available. This code works with TensorFlow 1.3 or 1.4.
3. Install requirements:
```
pip install -r requirements.txt
```
### Using a pre-trained model
1. **Download and unpack a model**:
```
curl http://data.keithito.com/data/speech/tacotron-20170720.tar.bz2 | tar xjC /tmp
```
2. **Run the demo server**:
```
python3 demo_server.py --checkpoint /tmp/tacotron-20170720/model.ckpt
```
3. **Point your browser at localhost:9000**
* Type what you want to synthesize
### Training
*Note: you need at least 40GB of free disk space to train a model.*
1. **Download a speech dataset.**
The following are supported out of the box:
* [LJ Speech](https://keithito.com/LJ-Speech-Dataset/) (Public Domain)
* [Blizzard 2012](http://www.cstr.ed.ac.uk/projects/blizzard/2012/phase_one) (Creative Commons Attribution Share-Alike)
You can use other datasets if you convert them to the right format. See [TRAINING_DATA.md](TRAINING_DATA.md) for more info.
2. **Unpack the dataset into `~/tacotron`**
After unpacking, your tree should look like this for LJ Speech:
```
tacotron
|- LJSpeech-1.0
|- metadata.csv
|- wavs
```
or like this for Blizzard 2012:
```
tacotron
|- Blizzard2012
|- ATrampAbroad
| |- sentence_index.txt
| |- lab
| |- wav
|- TheManThatCorruptedHadleyburg
|- sentence_index.txt
|- lab
|- wav
```
3. **Preprocess the data**
```
python3 preprocess.py --dataset ljspeech
```
* Use `--dataset blizzard` for Blizzard data
4. **Train a model**
```
python3 train.py
```
Tunable hyperparameters are found in [hparams.py](hparams.py). You can adjust these at the command
line using the `--hparams` flag, for example `--hparams="batch_size=16,outputs_per_step=2"`.
Hyperparameters should generally be set to the same values at both training and eval time.
5. **Monitor with Tensorboard** (optional)
```
tensorboard --logdir ~/tacotron/logs-tacotron
```
The trainer dumps audio and alignments every 1000 steps. You can find these in
`~/tacotron/logs-tacotron`.
6. **Synthesize from a checkpoint**
```
python3 demo_server.py --checkpoint ~/tacotron/logs-tacotron/model.ckpt-185000
```
Replace "185000" with the checkpoint number that you want to use, then open a browser
to `localhost:9000` and type what you want to speak. Alternately, you can
run [eval.py](eval.py) at the command line:
```
python3 eval.py --checkpoint ~/tacotron/logs-tacotron/model.ckpt-185000
```
If you set the `--hparams` flag when training, set the same value here.
## Notes and Common Issues
* [TCMalloc](http://goog-perftools.sourceforge.net/doc/tcmalloc.html) seems to improve
training speed and avoids occasional slowdowns seen with the default allocator. You
can enable it by installing it and setting `LD_PRELOAD=/usr/lib/libtcmalloc.so`.
* You can train with [CMUDict](http://www.speech.cs.cmu.edu/cgi-bin/cmudict) by downloading the
dictionary to ~/tacotron/training and then passing the flag `--hparams="use_cmudict=True"` to
train.py. This will allow you to pass ARPAbet phonemes enclosed in curly braces at eval
time to force a particular pronunciation, e.g. `Turn left on {HH AW1 S S T AH0 N} Street.`
* If you pass a Slack incoming webhook URL as the `--slack_url` flag to train.py, it will send
you progress updates every 1000 steps.
* Occasionally, you may see a spike in loss and the model will forget how to attend (the
alignments will no longer make sense). Although it will recover eventually, it may
save time to restart at a checkpoint prior to the spike by passing the
`--restore_step=150000` flag to train.py (replacing 150000 with a step number prior to the
spike). **Update**: a recent [fix](https://github.com/keithito/tacotron/pull/7) to gradient
clipping by @candlewill may have fixed this.
* During eval and training, audio length is limited to `max_iters * outputs_per_step * frame_shift_ms`
milliseconds. With the defaults (max_iters=200, outputs_per_step=5, frame_shift_ms=12.5), this is
12.5 seconds.
If your training examples are longer, you will see an error like this:
`Incompatible shapes: [32,1340,80] vs. [32,1000,80]`
To fix this, you can set a larger value of `max_iters` by passing `--hparams="max_iters=300"` to
train.py (replace "300" with a value based on how long your audio is and the formula above).
## Other Implementations
* By Alex Barron: https://github.com/barronalex/Tacotron
* By Kyubyong Park: https://github.com/Kyubyong/tacotron
Copyright (c) 2017 Keith Ito

2
requirements.txt
View File

@ -1,10 +1,8 @@
# Note: this doesn't include tensorflow or tensorflow-gpu because the package you need to install
# depends on your platform. It is assumed you have already installed tensorflow.
falcon==1.2.0
inflect==0.2.5
librosa==0.5.1
matplotlib==2.0.2
numpy==1.13.0
scipy==0.19.0
tqdm==4.11.2
Unidecode==0.4.20

41
tests/numbers_test.py
View File

@ -2,40 +2,39 @@ from text.numbers import normalize_numbers
def test_normalize_numbers():
assert normalize_numbers('0') == 'zero'
assert normalize_numbers('1') == 'one'
assert normalize_numbers('15') == 'fifteen'
assert normalize_numbers('24') == 'twenty-four'
assert normalize_numbers('24') == 'twenty four'
assert normalize_numbers('100') == 'one hundred'
assert normalize_numbers('101') == 'one hundred one'
assert normalize_numbers('456') == 'four hundred fifty-six'
assert normalize_numbers('456') == 'four hundred fifty six'
assert normalize_numbers('1000') == 'one thousand'
assert normalize_numbers('1800') == 'eighteen hundred'
assert normalize_numbers('2,000') == 'two thousand'
assert normalize_numbers('3000') == 'three thousand'
assert normalize_numbers('18000') == 'eighteen thousand'
assert normalize_numbers('24,000') == 'twenty-four thousand'
assert normalize_numbers('124,001') == 'one hundred twenty-four thousand one'
assert normalize_numbers('24,000') == 'twenty four thousand'
assert normalize_numbers('124,001') == 'one hundred twenty four thousand one'
assert normalize_numbers('999,999') == 'nine hundred ninety nine thousand nine hundred ninety nine'
assert normalize_numbers('1000000002') == 'one billion two'
assert normalize_numbers('1200000000') == 'one billion two hundred million'
assert normalize_numbers('19800000004001') == 'nineteen trillion eight hundred billion four thousand one'
assert normalize_numbers('712000000000000000') == 'seven hundred twelve quadrillion'
assert normalize_numbers('1000000000000000000') == '1000000000000000000'
assert normalize_numbers('6.4 sec') == 'six point four sec'
def test_normalize_ordinals():
assert normalize_numbers('1st') == 'first'
assert normalize_numbers('2nd') == 'second'
assert normalize_numbers('5th') == 'fifth'
assert normalize_numbers('9th') == 'ninth'
assert normalize_numbers('243rd place') == 'two hundred and forty-third place'
def test_normalize_dates():
assert normalize_numbers('1400') == 'fourteen hundred'
assert normalize_numbers('1901') == 'nineteen oh one'
assert normalize_numbers('1999') == 'nineteen ninety-nine'
assert normalize_numbers('2000') == 'two thousand'
assert normalize_numbers('2004') == 'two thousand four'
assert normalize_numbers('2010') == 'twenty ten'
assert normalize_numbers('2012') == 'twenty twelve'
assert normalize_numbers('2025') == 'twenty twenty-five'
assert normalize_numbers('September 11, 2001') == 'September eleven, two thousand one'
assert normalize_numbers('July 26, 1984.') == 'July twenty-six, nineteen eighty-four.'
assert normalize_numbers('15th') == 'fifteenth'
assert normalize_numbers('212th street') == 'two hundred twelfth street'
assert normalize_numbers('243rd place') == 'two hundred forty third place'
assert normalize_numbers('1025th') == 'one thousand twenty fifth'
assert normalize_numbers('1000000th') == 'one millionth'
def test_normalize_money():
@ -43,9 +42,9 @@ def test_normalize_money():
assert normalize_numbers('$1') == 'one dollar'
assert normalize_numbers('$10') == 'ten dollars'
assert normalize_numbers('$.01') == 'one cent'
assert normalize_numbers('$0.25') == 'twenty-five cents'
assert normalize_numbers('$0.25') == 'twenty five cents'
assert normalize_numbers('$5.00') == 'five dollars'
assert normalize_numbers('$5.01') == 'five dollars, one cent'
assert normalize_numbers('$135.99.') == 'one hundred thirty-five dollars, ninety-nine cents.'
assert normalize_numbers('$135.99.') == 'one hundred thirty five dollars, ninety nine cents.'
assert normalize_numbers('$40,000') == 'forty thousand dollars'
assert normalize_numbers('for £2500!') == 'for twenty-five hundred pounds!'
assert normalize_numbers('for £2500!') == 'for twenty five hundred pounds!'

13
tests/text_test.py
View File

@ -31,13 +31,6 @@ def test_collapse_whitespace():
assert cleaners.collapse_whitespace(' x. y, \tz') == ' x. y, z'
def test_convert_to_ascii():
assert cleaners.convert_to_ascii("raison d'être") == "raison d'etre"
assert cleaners.convert_to_ascii('grüß gott') == 'gruss gott'
assert cleaners.convert_to_ascii('안녕') == 'annyeong'
assert cleaners.convert_to_ascii('Здравствуйте') == 'Zdravstvuite'
def test_lowercase():
assert cleaners.lowercase('Happy Birthday!') == 'happy birthday!'
assert cleaners.lowercase('CAFÉ') == 'café'
@ -48,13 +41,13 @@ def test_expand_abbreviations():
def test_expand_numbers():
assert cleaners.expand_numbers('3 apples and 44 pears') == 'three apples and forty-four pears'
assert cleaners.expand_numbers('3 apples and 44 pears') == 'three apples and forty four pears'
assert cleaners.expand_numbers('$3.50 for gas.') == 'three dollars, fifty cents for gas.'
def test_cleaner_pipelines():
text = 'Mr. Müller ate 2 Apples'
assert cleaners.english_cleaners(text) == 'mister muller ate two apples'
assert cleaners.transliteration_cleaners(text) == 'mr. muller ate 2 apples'
assert cleaners.english_cleaners(text) == 'mister mller ate two apples'
assert cleaners.transliteration_cleaners(text) == 'mr. mller ate 2 apples'
assert cleaners.basic_cleaners(text) == 'mr. müller ate 2 apples'

7
text/cleaners.py
View File

@ -4,14 +4,11 @@ Cleaners are transformations that run over the input text at both training and e
Cleaners can be selected by passing a comma-delimited list of cleaner names as the "cleaners"
hyperparameter. Some cleaners are English-specific. You'll typically want to use:
1. "english_cleaners" for English text
2. "transliteration_cleaners" for non-English text that can be transliterated to ASCII using
the Unidecode library (https://pypi.python.org/pypi/Unidecode)
3. "basic_cleaners" if you do not want to transliterate (in this case, you should also update
2. "basic_cleaners" if you do not want to transliterate (in this case, you should also update
the symbols in symbols.py to match your data).
'''
import re
from unidecode import unidecode
from .numbers import normalize_numbers
@ -60,7 +57,7 @@ def collapse_whitespace(text):
def convert_to_ascii(text):
return unidecode(text)
return re.sub(r'[^\x00-\x7F]+', '', text) # This simply strips non-ASCII characters.
def basic_cleaners(text):

111
text/numbers.py
View File

@ -1,15 +1,68 @@
import inflect
import re
_inflect = inflect.engine()
_comma_number_re = re.compile(r'([0-9][0-9\,]+[0-9])')
_decimal_number_re = re.compile(r'([0-9]+\.[0-9]+)')
_pounds_re = re.compile(r'£([0-9\,]*[0-9]+)')
_dollars_re = re.compile(r'\$([0-9\.\,]*[0-9]+)')
_ordinal_re = re.compile(r'[0-9]+(st|nd|rd|th)')
_ordinal_re = re.compile(r'([0-9]+)(st|nd|rd|th)')
_number_re = re.compile(r'[0-9]+')
_units = [
'',
'one',
'two',
'three',
'four',
'five',
'six',
'seven',
'eight',
'nine',
'ten',
'eleven',
'twelve',
'thirteen',
'fourteen',
'fifteen',
'sixteen',
'seventeen',
'eighteen',
'nineteen'
]
_tens = [
'',
'ten',
'twenty',
'thirty',
'forty',
'fifty',
'sixty',
'seventy',
'eighty',
'ninety',
]
_digit_groups = [
'',
'thousand',
'million',
'billion',
'trillion',
'quadrillion',
]
_ordinal_suffixes = [
('one', 'first'),
('two', 'second'),
('three', 'third'),
('five', 'fifth'),
('eight', 'eighth'),
('nine', 'ninth'),
('twelve', 'twelfth'),
('ty', 'tieth'),
]
def _remove_commas(m):
return m.group(1).replace(',', '')
@ -40,23 +93,47 @@ def _expand_dollars(m):
return 'zero dollars'
def _expand_ordinal(m):
return _inflect.number_to_words(m.group(0))
def _standard_number_to_words(n, digit_group):
parts = []
if n >= 1000:
# Format next higher digit group.
parts.append(_standard_number_to_words(n // 1000, digit_group + 1))
n = n % 1000
if n >= 100:
parts.append('%s hundred' % _units[n // 100])
if n % 100 >= len(_units):
parts.append(_tens[(n % 100) // 10])
parts.append(_units[(n % 100) % 10])
else:
parts.append(_units[n % 100])
if n > 0:
parts.append(_digit_groups[digit_group])
return ' '.join([x for x in parts if x])
def _number_to_words(n):
# Handle special cases first, then go to the standard case:
if n >= 1000000000000000000:
return str(n) # Too large, just return the digits
elif n == 0:
return 'zero'
elif n % 100 == 0 and n % 1000 != 0 and n < 3000:
return _standard_number_to_words(n // 100, 0) + ' hundred'
else:
return _standard_number_to_words(n, 0)
def _expand_number(m):
num = int(m.group(0))
if num > 1000 and num < 3000:
if num == 2000:
return 'two thousand'
elif num > 2000 and num < 2010:
return 'two thousand ' + _inflect.number_to_words(num % 100)
elif num % 100 == 0:
return _inflect.number_to_words(num // 100) + ' hundred'
else:
return _inflect.number_to_words(num, andword='', zero='oh', group=2).replace(', ', ' ')
else:
return _inflect.number_to_words(num, andword='')
return _number_to_words(int(m.group(0)))
def _expand_ordinal(m):
num = _number_to_words(int(m.group(1)))
for suffix, replacement in _ordinal_suffixes:
if num.endswith(suffix):
return num[:-len(suffix)] + replacement
return num + 'th'
def normalize_numbers(text):