stressonnx 0.0.2__tar.gz

stressonnx-0.0.2/LICENSE

@@ -0,0 +1,202 @@
+
+                                 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 2026 TigreGotico Lda
+
+   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.

stressonnx-0.0.2/MANIFEST.in

@@ -0,0 +1 @@
+include version.py

stressonnx-0.0.2/PKG-INFO

@@ -0,0 +1,313 @@
+Metadata-Version: 2.4
+Name: stressonnx
+Version: 0.0.2
+Summary: Pure-onnxruntime multi-language word-stress / accentuation
+Author-email: JarbasAI <jarbasai@mailfence.com>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/TigreGotico/stressonnx
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: onnxruntime
+Requires-Dist: huggingface_hub
+Requires-Dist: tokenizers
+Provides-Extra: export
+Requires-Dist: torch; extra == "export"
+Requires-Dist: silero_stress; extra == "export"
+Provides-Extra: test
+Requires-Dist: pytest; extra == "test"
+Requires-Dist: hypothesis; extra == "test"
+Dynamic: license-file
+
+# stressonnx
+
+Multi-language **word-stress placement** ("accentuation") for text, built for
+TTS front-ends.  Pure `onnxruntime + numpy` at runtime — **no torch, ever**.
+
+```python
+from stressonnx import stress
+
+stress("старинный замок стоит на горе", "ru")   # 'стари́нный за́мок сто́ит на горе́'
+stress("дверной замок надёжен", "ru")           # 'дверно́й замо́к надёжен'
+```
+
+Same spelling, different word: за́мок is a castle, замо́к is a lock.  stressonnx
+reads the sentence, decides which one you meant, and marks the stressed vowel.
+
+---
+
+## Why word stress?
+
+**Word stress** (lexical stress) is which syllable of a word is pronounced
+prominently: English *REcord* (noun) vs *reCORD* (verb).  A text-to-speech
+system must know it before it can pick the right sounds — in Russian,
+unstressed vowels *reduce* (о sounds like а), so getting the stress wrong
+changes every vowel in the word, not just the melody.
+
+Whether **you** need this library depends on how your language writes stress:
+
+| Orthography type | Examples | What you need |
+|---|---|---|
+| Stress is free/mobile and **not written** | Russian, Ukrainian, Belarusian, most languages here | **A stress model — this library.**  Nothing in the spelling of `замок` tells you which syllable to stress; only context does. |
+| Stress is **predictable by rule** | Kazakh/Turkic (final syllable), Armenian, Georgian | A positional rule covers most words — that is the `simple` backend: a curated exception vocabulary plus a per-language default rule. |
+| Stress is **already written** | Spanish, Greek, Portuguese | You do **not** need stressonnx — the orthography (accent rules) already encodes it.  But you may still need *sense* disambiguation, see below. |
+
+**The Portuguese case (why "stress is written" isn't the end of the story):**
+Portuguese spelling pins down the stressed syllable, yet pairs like *sede*
+(thirst /ˈsedɨ/ vs headquarters /ˈsɛdɨ/) share spelling *and* stress position
+while differing in vowel **quality** — resolvable only from meaning.  Our
+sibling library [bifonia](https://github.com/TigreGotico/bifonia) solves that
+with the same "disambiguate before G2P" idea used here: its
+`add_extra_diacritics(text)` rewrites the homograph with an explicit
+open/closed-vowel diacritic (*séde*/*sêde*) so any downstream phonemizer gets
+it right.  Rule of thumb: **unwritten stress → stressonnx; written stress but
+sense-dependent pronunciation → a bifonia-style diacritic restorer.**
+
+---
+
+## Supported languages
+
+| Model id | Languages | What it is | Measured quality |
+|----------|-----------|------------|------------------|
+| `ruaccent` | `ru` (default) | Homograph-aware 4-model ONNX pipeline (derived from [RUAccent](https://github.com/Den4ikAI/ruaccent), Apache-2.0) | 0.938 word accuracy, **0.820 on homographs** |
+| `silero` | `uk`, `be` (defaults), `ru` | Neural ONNX pipeline exported from [silero_stress](https://github.com/snakers4/silero-stress) (MIT); the `ru` variant also restores е→ё | ru 0.914 / uk 0.785 / be 0.873 |
+| `simple` | 26 languages¹ | Curated vocabulary + per-language positional rule; no neural inference | parity-locked to upstream / sourced rules, see scoreboard |
+
+¹ `ru uk be bg mk sl lv hy ka kk ky tt ba cv sah kjh tg udm mdf myv kbd xal
+az-Latn az-Cyrl uz-Latn uz-Cyrl` — Russian, Ukrainian, Belarusian (all
+dictionary-path), Bulgarian, Macedonian, Slovene, Latvian, Armenian,
+Georgian, Kazakh, Kyrgyz, Tatar, Bashkir, Chuvash, Yakut, Khakas, Tajik,
+Udmurt, Moksha, Erzya, Kabardian, Kalmyk, Azerbaijani (both scripts), Uzbek
+(both scripts).  Every language — including ru/uk/be — has a torch-free,
+ONNX-free rule/vocabulary path (`model="simple"`), so `fallback=True` always
+bottoms out in a model that needs nothing but a small vocabulary file.
+
+Numbers come from the committed, reproducible
+[benchmark scoreboard](benchmarks/RESULTS.md) (annotated UD-treebank gold;
+read its noise-ceiling note before quoting absolutes).  Defaults per
+language: `ru → ruaccent`, `uk/be → silero`, everything else → `simple`.
+
+Models are hosted on
+[TigreGotico/stressonnx-models](https://huggingface.co/TigreGotico/stressonnx-models)
+and downloaded automatically on first use (see *Offline & failure behavior*).
+
+---
+
+## Install
+
+```bash
+pip install stressonnx
+```
+
+Runtime dependencies: `onnxruntime`, `numpy`, `huggingface_hub`, and
+`tokenizers` (used only by the `ru` ruaccent pipeline).  Optional:
+
+- `razdel` — better Russian sentence splitting inside the ruaccent pipeline
+  (`pip install razdel`); without it the whole input is processed as one span.
+- `pip install stressonnx[export]` — torch + silero_stress, **only** for
+  re-exporting models from a checkout (never needed at runtime).
+
+---
+
+## Usage
+
+```python
+from stressonnx import StressPipeline, analyze, stress, to_plus_notation
+
+# One-shot function (caches model instances internally)
+stress("Привіт світ", "uk")                   # 'Приві́т сві́т'
+stress("Сәлем Қазақстан", "kk")               # 'Сәле́м Қазақста́н'
+
+# Pick a specific model, or a capability instead of a model id
+stress("красивый город", "ru", model="silero")    # 'краси́вый го́род'
+stress("красивый город", "ru", model="simple")    # 'краси́вый го́род'
+stress("красивый город", "ru", prefer="fast")     # 'краси́вый го́род'  (silero)
+
+# An isolated engine with its own cache and failure policy
+pipeline = StressPipeline()
+pipeline.stress("замок стоит на горе", "ru")                      # 'за́мок сто́ит на горе́'
+```
+
+### Structured results: `analyze()`
+
+For TTS pipelines that need to reason about individual words rather than a
+marked string, `analyze()` returns a `StressResult`: per-word spans with
+offsets into the **original, untouched input**.
+
+```python
+result = analyze("замок стоит на горе", "ru")
+result.text     # 'за́мок сто́ит на горе́'  (same as stress())
+
+for w in result.words:
+    print(w.text, w.start, w.end, w.stressed_index, w.yo_restored)
+# замок 0 5 1 False
+# стоит 6 11 2 False
+# на 12 14 None False
+# горе 15 19 2 False
+```
+
+`w.stressed_index` is the offset of the stressed vowel *within the word*
+(`None` if the word carries no mark); `w.yo_restored` is `True` when the
+backend rewrote е→ё inside that word.  Because offsets refer to `result.original`
+exactly as passed in, callers never need to re-parse the marked string to
+locate a word.
+
+### Batches: `stress_batch()`
+
+```python
+from stressonnx import stress_batch
+
+stress_batch(["привет", "мир"], "ru")   # ['приве́т', 'мир']
+```
+
+### Output notation
+
+All backends emit the **combining acute accent** (U+0301) *after* the
+stressed vowel — `приве́т` is `п р и в е U+0301 т`.  For TTS models trained on
+the `+`-before-vowel format:
+
+```python
+stress("привет", "ru", notation="plus")   # 'прив+ет'
+to_plus_notation("приве́т")                # 'прив+ет'  (handles NFC-composed á too)
+```
+
+### ё restoration (Russian)
+
+Both Russian neural backends restore ё that writers commonly type as е:
+`зеленый → зелё́ный`.  Genuinely ambiguous ё-homographs (все/всё) are resolved
+by `ruaccent` from context and deliberately left untouched by `silero`.
+
+---
+
+## Offline & failure behavior
+
+- **First call per language downloads models** into the standard Hugging Face
+  cache (`~/.cache/huggingface`, relocatable via `HF_HOME`).  Sizes: `ru`
+  ruaccent ≈ 500 MB, silero ≈ tens of MB, `simple` languages ≈ 1 MB.
+- **Warm-up ahead of serving:** call `warm_up(lang)` once at startup so no
+  synthesis request ever blocks on a model download; it loads the same
+  cached instance later `stress()` calls use.
+- **Fully offline:** after a warm run, set `HF_HUB_OFFLINE=1` — cached models
+  keep working, network is never touched.
+- **Typed failures:**
+
+```python
+from stressonnx import stress, UnsupportedLanguageError, ModelDownloadError
+
+try:
+    out = stress(text, lang, fallback=True)   # opt-in: walk ruaccent→silero→simple
+except UnsupportedLanguageError as e:         # also catchable as ValueError
+    out = text                                # e.supported lists valid tags
+except ModelDownloadError as e:               # names the exact missing HF path
+    out = text
+```
+
+`fallback=True` degrades down the quality chain with a logged warning per
+hop (it also engages on `ModelLoadError` — a corrupt cache — not just
+failed downloads); the default (`False`) raises immediately.  A failed
+(lang, model) pair is not retried for 30 s, so an outage never triggers a
+download attempt per call.
+
+**Supply-chain pinning:** model files are fetched from a commit-pinned
+revision of the HF repo (`HF_REPO_REVISION` in `stressonnx/registry.py`),
+so releases are reproducible and upstream changes never reach users
+implicitly.
+
+**Thread safety:** `stress()` and the backends use double-checked locking
+for lazy loads; calling from multiple threads is supported (onnxruntime
+sessions are thread-safe for inference).
+
+### Contracts worth knowing
+
+- `simple`/`silero` **skip** words already carrying U+0301; `ruaccent`
+  **strips and re-derives** (wrong input marks get corrected).
+- Monosyllables: `simple`/`silero` always stress them; `ruaccent` usually
+  leaves bare single-vowel words unmarked.
+- `ruaccent` normalizes its input (drops symbols like `…`, collapses runs of
+  whitespace) — it is not byte-layout-preserving; the other backends are.
+- Russian hyphenated clitics (`кто́-то`, `како́й-нибудь`, `-либо`, `-таки`,
+  `-ка`) never receive a mark on the particle.
+
+---
+
+## Guarding by writing system
+
+Feeding Cyrillic to the Georgian model (or vice versa) is a silent no-op — the
+input never matches the model's alphabet.  Check first:
+
+```python
+from stressonnx import lang_to_script, MODEL_REGISTRY
+
+if lang_to_script(lang) in MODEL_REGISTRY[model_id].input_scripts:
+    text = stress(text, lang, model=model_id)
+```
+
+`Script` values (`"cyrillic"`, `"latin"`, `"armenian"`, `"georgian"`) are
+plain strings shared with phoonnx's `Alphabet` enum for direct comparison.
+
+---
+
+## Adding a language
+
+Two paths, both documented step-by-step for newcomers in
+[`export/ADDING_A_LANGUAGE.md`](export/ADDING_A_LANGUAGE.md):
+
+1. **You have a stressed wordlist** → ship a `simple` language: package the
+   vocabulary, declare alphabet/vowels/OOV rule, upload to the HF repo,
+   register the language tag.  No training, no torch.
+2. **You have (or train) a neural accentor** → export it to ONNX with the
+   scripts in `export/` and add a backend entry.
+
+All 20 upstream silero_stress vocabularies are already shipped, and
+`export/build_wiktionary_vocab.py` turns any language whose Wiktionary
+headwords carry stress marks into a `simple` language (that is how
+Bulgarian, Macedonian, Slovene, Latvian and Ukrainian were built; Russian
+came from the RUAccent pronunciation dictionary).
+
+---
+
+## Documentation
+
+Pick your entry point:
+
+- **New to all of this?**  The [Why word stress?](#why-word-stress) section
+  above, then [`docs/languages.md`](docs/languages.md) — a plain-language,
+  per-language guide to why stress marking is needed and what we do about it.
+- **Developer integrating stressonnx?**  [Usage](#usage) above, then
+  [`docs/models.md`](docs/models.md) for backend contracts and
+  [`docs/architecture.md`](docs/architecture.md) for the package internals.
+- **Linguist checking our homework?**  [`docs/languages.md`](docs/languages.md)
+  carries the typology and per-rule citations;
+  [`benchmarks/RESULTS.md`](benchmarks/RESULTS.md) the measurements; every
+  OOV rule's source is quoted in `stressonnx/backends/simple.py`.
+
+- [`docs/languages.md`](docs/languages.md) — per-language guide: stress
+  system, why TTS needs it, what stressonnx does, with citations.
+- [`docs/models.md`](docs/models.md) — every backend in depth: pipeline
+  stages, per-language rules, quality numbers, contracts.
+- [`docs/architecture.md`](docs/architecture.md) — package layout, the single
+  download layer, data flow.
+- [`benchmarks/RESULTS.md`](benchmarks/RESULTS.md) — the scoreboard and how to
+  reproduce it.
+- [`examples/`](examples/) — runnable scripts, from basics to homograph demos.
+
+## Related projects
+
+- [phoonnx](https://github.com/TigreGotico/phoonnx) — ONNX TTS engine; calls
+  stressonnx before phonemization for Russian voices.
+- [bifonia](https://github.com/TigreGotico/bifonia) — European-Portuguese
+  homograph disambiguation by meaning (the "written stress, unwritten vowel
+  quality" counterpart to this library).
+- [scriptconv](https://github.com/TigreGotico/scriptconv) — script detection
+  and phoneme-notation conversion.
+- [silabificador](https://github.com/TigreGotico/silabificador) — Portuguese
+  syllabification and stress by rule.
+
+## License
+
+Apache-2.0.  Model attributions: RUAccent (Den4ikAI, Apache-2.0),
+silero_stress (snakers4, MIT).