kitten-text-processing 0.1.0__tar.gz

kitten_text_processing-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "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.

kitten_text_processing-0.1.0/LICENSE-SACREMOSES

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2020 alvations
+
+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:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+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.

kitten_text_processing-0.1.0/MANIFEST.in

@@ -0,0 +1,4 @@
+include LICENSE LICENSE-SACREMOSES NOTICE
+recursive-include kitten_text_processing/data *.gz *.json
+recursive-include tests *.py *.txt *.json *.jsonl *.md
+recursive-include tools *.py *.txt

kitten_text_processing-0.1.0/NOTICE

@@ -0,0 +1,26 @@
+Kitten Text Processing
+
+Bundled grammar data is derived from NVIDIA NeMo Text Processing 1.2.0:
+https://github.com/NVIDIA/NeMo-text-processing
+Copyright NVIDIA CORPORATION and NeMo contributors.
+Licensed under the Apache License, Version 2.0 (see LICENSE).
+
+_token_parser.py, _ordering.py, and _punctuation.py are adapted from
+NeMo Text Processing 1.2.0. Original copyright notices are retained.
+The grammar exporter preserves the upstream cased grammar weights and labels.
+Russian uses deterministic=False, as required by the upstream grammar.
+
+The byte-transducer decoder and package interface are implemented here using
+only the Python standard library. No Pynini, OpenFst, or NeMo executable code
+is required at runtime. OpenFst's documented shortest-path queue ordering
+informs the decoder's tie-breaking behavior.
+
+The unchanged text-normalization fixtures in tests/upstream are from NeMo
+r1.2.0, commit 7efa127d968c081793ebf11fa94dfb4257302d48 (Apache-2.0).
+
+_unicode_data.py contains Unicode character tables exported from Sacremoses
+0.2.0, copyright Sacremoses contributors, licensed under the MIT License
+(see LICENSE-SACREMOSES). _detokenize.py reproduces its relevant behavior.
+
+The output-epsilon removal ordering follows the OpenFst RmEpsilon algorithm
+(Copyright Google, Inc., Apache-2.0); the implementation here uses Python.

kitten_text_processing-0.1.0/PKG-INFO

@@ -0,0 +1,132 @@
+Metadata-Version: 2.4
+Name: kitten-text-processing
+Version: 0.1.0
+Summary: Standalone, standard-library-only multilingual text normalization for TTS
+License-Expression: Apache-2.0 AND MIT
+Project-URL: Homepage, https://github.com/KittenML/kitten-text-processing
+Project-URL: Repository, https://github.com/KittenML/kitten-text-processing
+Project-URL: Issues, https://github.com/KittenML/kitten-text-processing/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: LICENSE-SACREMOSES
+License-File: NOTICE
+Dynamic: license-file
+
+# Kitten Text Processing
+
+A standalone multilingual written-to-spoken normalizer with **zero runtime
+dependencies**. It uses Python's standard library to interpret bundled NeMo
+1.2.0 grammar data. No NeMo, Pynini, OpenFst, models, network access, or grammar
+compilation is needed when installing or running the library.
+
+```sh
+pip install kitten-text-processing
+python -m kitten_text_processing --lang en 'I paid $12.50 for 3 books.'
+```
+
+```python
+from kitten_text_processing import normalize_text, warm, Normalizer
+
+warm()  # optional; load English ahead of the first call
+normalize_text('I paid $12.50 for 3 books.')
+# 'I paid twelve dollars fifty cents for three books.'
+normalize_text('Tengo 2 gatos.', locale='es-ES')
+# 'Tengo dos gatos.'
+
+normalizer = Normalizer(input_case='cased', lang='ja')
+normalizer.normalize('猫が2匹います。', punct_post_process=True)
+```
+
+Languages: `en es fr de pt it zh ja ko hi ar ru vi hu sv hy rw`.
+Locale tags such as `en-US`, `pt-BR`, `zh-CN`, and `hi_IN` select the corresponding
+language grammar; they do not select separate regional grammars. Python 3.10+.
+
+## Convenience API
+
+`normalize_text(text, locale='en-US', return_spans=False)` normalizes text and
+cleans up punctuation. `warm(locale='en-US')` preloads a language grammar.
+`PRESERVES_SENTINELS` indicates that private-use expression markers are retained.
+
+`return_spans=True` raises `NotImplementedError`. Empty values are preserved by
+`normalize_text`; `Normalizer.normalize` requires a string. Unsupported languages
+raise `ValueError`.
+
+## Design and scope
+
+The runtime is Python code plus about 14 MB of compressed, portable grammar
+arrays. It runs weighted byte transducers over UTF-8, parses the classified
+tokens, tries the upstream field-order permutations, then verbalizes and applies
+punctuation cleanup. Grammars are loaded lazily per language. The convenience
+API retains at most four normalizers; explicit instances let callers control
+lifetime. Instances are safe to call concurrently. Normalize sentence-sized
+chunks: ambiguous long inputs can build large intermediate lattices.
+
+The cased written-to-spoken grammars from the pinned NeMo release are included.
+Inverse normalization, audio rescoring, custom whitelists, grammar compilation,
+and separate `lower_cased` grammar variants are outside this package's scope.
+Korean and Armenian also accept `lower_cased`: their upstream graphs were verified
+to be identical to their cased graphs.
+Russian uses NeMo's non-deterministic grammar and chooses a minimum-weight
+reading; this is not a context-sensitive grammatical disambiguator.
+
+Upstream limitations remain visible. In particular, Portuguese and Kinyarwanda
+can reject ordinary inputs; a no-path error is raised rather than silently
+claiming successful normalization. Some upstream outputs leave digits intact or
+choose linguistically awkward readings. Compatibility is not a claim of perfect
+linguistic correctness for all inputs.
+
+## Validation and reproduction
+
+For development, clone the repository and install locally with `pip install .`.
+
+The `tests/corpus` directory contains 1,000 manually authored input sentences
+across all 17 supported languages and separately recorded NeMo outputs. This is
+a regression corpus, not an untouched holdout or native-speaker quality audit.
+
+```sh
+# Standard-library-only checks and comparison with frozen reference outputs
+python -m unittest discover -s tests -v
+python tools/benchmark.py
+
+# Build-time/reference tooling only (never runtime dependencies)
+python -m venv .venv-reference
+.venv-reference/bin/pip install -r tools/requirements-reference.txt
+.venv-reference/bin/python tools/export_grammars.py
+.venv-reference/bin/python tools/benchmark.py --record-reference
+```
+
+**Expanded comparison: 22,976 exact outputs and 1,435 matching rejections, with
+zero mismatches across 24,411 cases.** Validation also includes the original 1,000 authored
+sentences, every one of the 5,407 upstream fixture inputs, and over 1,000 additional
+generated/edge cases per language. Accepted outputs must match exactly; matching
+rejections are counted separately. There are 18 original fixture expectations that
+NeMo itself disagrees with; these remain unchanged and are explicitly recorded.
+Audio/n-best fixture inputs are included, but audio rescoring is outside our scope.
+See [upstream provenance](https://github.com/KittenML/kitten-text-processing/blob/main/tests/upstream/README.md).
+
+The optimized engine is **1.8–7.8× faster than the previous implementation** on our
+warm-call benchmark. English improved from 65.7 to 23.8 ms per sentence (NeMo:
+7.7 ms); speed relative to NeMo varies by language. Measurements use 20
+sentences per language, three repetitions, warmed grammar indexes, and rotating
+execution order. Run `tools/speed_benchmark.py` in the reference environment to
+produce a local report. Generated benchmark results are excluded from Git.
+Grammar metadata records state/arc counts, upstream version, settings, and SHA-256 hashes.
+The exporter skips already exported languages; to rebuild one, remove its
+`metadata.json` and pass `--languages en` (or another language).
+
+To regenerate the expanded oracle suite (development dependencies required):
+
+```sh
+.venv-reference/bin/python tools/stress_test.py --case-source upstream --count 0 --output .cache/upstream-canonical
+.venv-reference/bin/python tools/stress_test.py --case-source generated --seed 20261002 --count 1000 --output .cache/generated-canonical
+python tools/freeze_extended.py .cache/upstream-canonical .cache/generated-canonical
+.venv-reference/bin/python tools/speed_benchmark.py
+```
+
+The package and NeMo-derived grammar data use Apache-2.0. Frozen Sacremoses
+Unicode tables use MIT. See `LICENSE`, `LICENSE-SACREMOSES`, and `NOTICE` for
+provenance and retained notices.

kitten_text_processing-0.1.0/README.md

@@ -0,0 +1,114 @@
+# Kitten Text Processing
+
+A standalone multilingual written-to-spoken normalizer with **zero runtime
+dependencies**. It uses Python's standard library to interpret bundled NeMo
+1.2.0 grammar data. No NeMo, Pynini, OpenFst, models, network access, or grammar
+compilation is needed when installing or running the library.
+
+```sh
+pip install kitten-text-processing
+python -m kitten_text_processing --lang en 'I paid $12.50 for 3 books.'
+```
+
+```python
+from kitten_text_processing import normalize_text, warm, Normalizer
+
+warm()  # optional; load English ahead of the first call
+normalize_text('I paid $12.50 for 3 books.')
+# 'I paid twelve dollars fifty cents for three books.'
+normalize_text('Tengo 2 gatos.', locale='es-ES')
+# 'Tengo dos gatos.'
+
+normalizer = Normalizer(input_case='cased', lang='ja')
+normalizer.normalize('猫が2匹います。', punct_post_process=True)
+```
+
+Languages: `en es fr de pt it zh ja ko hi ar ru vi hu sv hy rw`.
+Locale tags such as `en-US`, `pt-BR`, `zh-CN`, and `hi_IN` select the corresponding
+language grammar; they do not select separate regional grammars. Python 3.10+.
+
+## Convenience API
+
+`normalize_text(text, locale='en-US', return_spans=False)` normalizes text and
+cleans up punctuation. `warm(locale='en-US')` preloads a language grammar.
+`PRESERVES_SENTINELS` indicates that private-use expression markers are retained.
+
+`return_spans=True` raises `NotImplementedError`. Empty values are preserved by
+`normalize_text`; `Normalizer.normalize` requires a string. Unsupported languages
+raise `ValueError`.
+
+## Design and scope
+
+The runtime is Python code plus about 14 MB of compressed, portable grammar
+arrays. It runs weighted byte transducers over UTF-8, parses the classified
+tokens, tries the upstream field-order permutations, then verbalizes and applies
+punctuation cleanup. Grammars are loaded lazily per language. The convenience
+API retains at most four normalizers; explicit instances let callers control
+lifetime. Instances are safe to call concurrently. Normalize sentence-sized
+chunks: ambiguous long inputs can build large intermediate lattices.
+
+The cased written-to-spoken grammars from the pinned NeMo release are included.
+Inverse normalization, audio rescoring, custom whitelists, grammar compilation,
+and separate `lower_cased` grammar variants are outside this package's scope.
+Korean and Armenian also accept `lower_cased`: their upstream graphs were verified
+to be identical to their cased graphs.
+Russian uses NeMo's non-deterministic grammar and chooses a minimum-weight
+reading; this is not a context-sensitive grammatical disambiguator.
+
+Upstream limitations remain visible. In particular, Portuguese and Kinyarwanda
+can reject ordinary inputs; a no-path error is raised rather than silently
+claiming successful normalization. Some upstream outputs leave digits intact or
+choose linguistically awkward readings. Compatibility is not a claim of perfect
+linguistic correctness for all inputs.
+
+## Validation and reproduction
+
+For development, clone the repository and install locally with `pip install .`.
+
+The `tests/corpus` directory contains 1,000 manually authored input sentences
+across all 17 supported languages and separately recorded NeMo outputs. This is
+a regression corpus, not an untouched holdout or native-speaker quality audit.
+
+```sh
+# Standard-library-only checks and comparison with frozen reference outputs
+python -m unittest discover -s tests -v
+python tools/benchmark.py
+
+# Build-time/reference tooling only (never runtime dependencies)
+python -m venv .venv-reference
+.venv-reference/bin/pip install -r tools/requirements-reference.txt
+.venv-reference/bin/python tools/export_grammars.py
+.venv-reference/bin/python tools/benchmark.py --record-reference
+```
+
+**Expanded comparison: 22,976 exact outputs and 1,435 matching rejections, with
+zero mismatches across 24,411 cases.** Validation also includes the original 1,000 authored
+sentences, every one of the 5,407 upstream fixture inputs, and over 1,000 additional
+generated/edge cases per language. Accepted outputs must match exactly; matching
+rejections are counted separately. There are 18 original fixture expectations that
+NeMo itself disagrees with; these remain unchanged and are explicitly recorded.
+Audio/n-best fixture inputs are included, but audio rescoring is outside our scope.
+See [upstream provenance](https://github.com/KittenML/kitten-text-processing/blob/main/tests/upstream/README.md).
+
+The optimized engine is **1.8–7.8× faster than the previous implementation** on our
+warm-call benchmark. English improved from 65.7 to 23.8 ms per sentence (NeMo:
+7.7 ms); speed relative to NeMo varies by language. Measurements use 20
+sentences per language, three repetitions, warmed grammar indexes, and rotating
+execution order. Run `tools/speed_benchmark.py` in the reference environment to
+produce a local report. Generated benchmark results are excluded from Git.
+Grammar metadata records state/arc counts, upstream version, settings, and SHA-256 hashes.
+The exporter skips already exported languages; to rebuild one, remove its
+`metadata.json` and pass `--languages en` (or another language).
+
+To regenerate the expanded oracle suite (development dependencies required):
+
+```sh
+.venv-reference/bin/python tools/stress_test.py --case-source upstream --count 0 --output .cache/upstream-canonical
+.venv-reference/bin/python tools/stress_test.py --case-source generated --seed 20261002 --count 1000 --output .cache/generated-canonical
+python tools/freeze_extended.py .cache/upstream-canonical .cache/generated-canonical
+.venv-reference/bin/python tools/speed_benchmark.py
+```
+
+The package and NeMo-derived grammar data use Apache-2.0. Frozen Sacremoses
+Unicode tables use MIT. See `LICENSE`, `LICENSE-SACREMOSES`, and `NOTICE` for
+provenance and retained notices.

kitten_text_processing-0.1.0/kitten_text_processing/__init__.py

@@ -0,0 +1,5 @@
+"""Dependency-free multilingual text normalization for speech synthesis."""
+from .normalizer import Normalizer, PRESERVES_SENTINELS, SUPPORTED_LANGUAGES, normalize_text, warm
+
+__version__ = '0.1.0'
+__all__ = ['Normalizer', 'PRESERVES_SENTINELS', 'SUPPORTED_LANGUAGES', 'normalize_text', 'warm']

kitten_text_processing-0.1.0/kitten_text_processing/__main__.py

@@ -0,0 +1,23 @@
+"""Command-line interface: python -m kitten_text_processing --lang es 'Tengo 2 gatos.'"""
+import argparse
+import sys
+from . import SUPPORTED_LANGUAGES, normalize_text
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Normalize written text for speech; no downloads or dependencies.')
+    parser.add_argument('text', nargs='?', help='Text to normalize; otherwise read stdin line by line')
+    parser.add_argument('--lang', default='en', help='Language code or locale (' + ', '.join(SUPPORTED_LANGUAGES) + ')')
+    args = parser.parse_args()
+    try:
+        if args.text is not None:
+            print(normalize_text(args.text, locale=args.lang))
+        else:
+            for line in sys.stdin:
+                print(normalize_text(line.rstrip('\n'), locale=args.lang))
+    except (ValueError, RuntimeError) as exc:
+        parser.exit(1, f'{exc}\n')
+
+
+if __name__ == '__main__':
+    main()

kitten_text_processing-0.1.0/kitten_text_processing/_detokenize.py

@@ -0,0 +1,62 @@
+"""Moses-compatible punctuation handling for the supported TN languages.
+
+Reimplemented using only re and Unicode character properties. NeMo calls Moses
+with a single string in a list, which is then split on whitespace.
+"""
+import re
+from bisect import bisect_right
+from ._unicode_data import ALPHA_RANGES, CURRENCY_SYMBOLS
+
+_ALPHA_STARTS = tuple(a for a, _ in ALPHA_RANGES)
+
+def _alpha(character):
+    value = ord(character)
+    i = bisect_right(_ALPHA_STARTS, value) - 1
+    return i >= 0 and value <= ALPHA_RANGES[i][1]
+
+_CJK = ((4352, 4607), (11904, 42191), (43072, 43135), (44032, 55215),
+        (63744, 64255), (65072, 65103), (65381, 65500), (94208, 101119),
+        (110592, 110895), (110960, 111359), (131072, 196607))
+
+
+def _cjk(c):
+    return any(a <= ord(c) <= b for a, b in _CJK)
+
+
+def detokenize(text, lang):
+    tokens = re.sub(r' @-@ ', '-', ' ' + text + ' ').split()
+    quotes = {}
+    space, result = ' ', ''
+    for i, token in enumerate(tokens):
+        if _cjk(token[0]) and lang != 'ko':
+            result += ('' if i and _cjk(tokens[i-1][-1]) else space) + token
+            space = ' '
+        elif all(c in CURRENCY_SYMBOLS or c in '([{¿¡' for c in token):
+            result += space + token
+            space = ''
+        elif re.fullmatch(r'[,\.?!:;\\%}\])]+', token):
+            result += (' ' if lang == 'fr' and re.fullmatch(r'[?!:;\\%]', token) else '') + token
+            space = ' '
+        elif lang == 'en' and i and len(token) > 1 and token[0] == "'" and _alpha(token[1]):
+            result += token
+            space = ' '
+        elif (lang in ('fr', 'it') and i+1 < len(tokens) and len(token) > 1
+              and token[-1] == "'" and _alpha(token[-2]) and _alpha(tokens[i+1][0])):
+            result += space + token
+            space = ''
+        elif re.fullmatch('[\'"„“`]+', token):
+            key = '"' if all(c in '„“”' for c in token) else token
+            count = quotes.get(key, 0)
+            if count % 2 or (lang == 'en' and token == "'" and i and tokens[i-1].endswith('s')):
+                result += token
+                space = ' '
+                if count % 2:
+                    quotes[key] = count + 1
+            else:
+                result += space + token
+                space = ''
+                quotes[key] = count + 1
+        else:
+            result += space + token
+            space = ' '
+    return re.sub(' {2,}', ' ', result).strip()