wakeforge 0.4.1a3__py3-none-any.whl

wakeforge-0.4.1a3.dist-info/METADATA

@@ -0,0 +1,208 @@
+Metadata-Version: 2.4
+Name: wakeforge
+Version: 0.4.1a3
+Summary: Full training and research suite for wake words — MFCC to HuBERT, all exported to ONNX
+Author-email: JarbasAi <jarbasai@mailfence.com>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/TigreGotico/ww_trainer
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch
+Requires-Dist: torchaudio
+Requires-Dist: onnx>=1.17
+Requires-Dist: onnxruntime>=1.20
+Requires-Dist: numpy
+Requires-Dist: soundfile
+Requires-Dist: click
+Requires-Dist: tqdm
+Requires-Dist: scikit-learn
+Requires-Dist: matplotlib
+Requires-Dist: librosa
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: onnxscript; extra == "dev"
+Requires-Dist: markovonnx; extra == "dev"
+Requires-Dist: umap-learn; extra == "dev"
+Requires-Dist: optuna; extra == "dev"
+Requires-Dist: voiceclonnx; extra == "dev"
+Provides-Extra: test
+Requires-Dist: pytest; extra == "test"
+Requires-Dist: pytest-cov; extra == "test"
+Requires-Dist: onnxscript; extra == "test"
+Requires-Dist: markovonnx; extra == "test"
+Requires-Dist: umap-learn; extra == "test"
+Requires-Dist: optuna; extra == "test"
+Requires-Dist: voiceclonnx; extra == "test"
+Provides-Extra: torchcodec
+Requires-Dist: torchcodec; extra == "torchcodec"
+Provides-Extra: mlflow
+Requires-Dist: mlflow; extra == "mlflow"
+Provides-Extra: sweep
+Requires-Dist: optuna; extra == "sweep"
+Provides-Extra: ocsvm
+Requires-Dist: scikit-learn>=1.3; extra == "ocsvm"
+Provides-Extra: transformers
+Requires-Dist: transformers; extra == "transformers"
+Provides-Extra: markov
+Requires-Dist: markovonnx; extra == "markov"
+Provides-Extra: vc
+Requires-Dist: voiceclonnx; extra == "vc"
+Provides-Extra: vc-onnx
+Requires-Dist: voiceclonnx; extra == "vc-onnx"
+Provides-Extra: datagen
+Requires-Dist: datasets; extra == "datagen"
+Requires-Dist: ovos-plugin-manager; extra == "datagen"
+Requires-Dist: ovos-tts-plugin-edge-tts; extra == "datagen"
+Requires-Dist: vadonnx>=0.1.0; extra == "datagen"
+Provides-Extra: mic
+Requires-Dist: sounddevice; extra == "mic"
+Provides-Extra: viz
+Requires-Dist: umap-learn; extra == "viz"
+Provides-Extra: notebooks
+Requires-Dist: jupyter; extra == "notebooks"
+Requires-Dist: nbconvert; extra == "notebooks"
+Requires-Dist: ipykernel; extra == "notebooks"
+Requires-Dist: datasets; extra == "notebooks"
+Requires-Dist: ovos-plugin-manager; extra == "notebooks"
+Requires-Dist: ovos-tts-plugin-edge-tts; extra == "notebooks"
+Requires-Dist: vadonnx>=0.1.0; extra == "notebooks"
+Dynamic: license-file
+
+# Wake Word Trainer
+
+A research-grade training suite for **wake-word detection** — the always-on
+keyword spotter that wakes "Hey Siri", "OK Google", or your own custom phrase.
+Train, evaluate, and ship lightweight on-device detectors that run anywhere
+from an ESP32 to a GPU server. Every component exports to ONNX; production
+inference requires only `onnxruntime` and `numpy` — no PyTorch at runtime.
+
+## What is a wake word?
+
+A short phrase ("hey jarvis", "computer", "alexa") that a device listens for
+continuously. When detected, downstream STT/NLU runs. A useful detector must
+run on tiny hardware (sub-100 KB, <10 % CPU, no internet), tolerate noise and
+distance, almost never false-fire (< 1 FA / hour), and trigger reliably when
+spoken (> 90 % recall at that operating point). ww-trainer is the toolchain
+that builds such a detector from a single phrase — synthesise data, train,
+evaluate, export, deploy.
+
+## Who is this for?
+
+| You are… | Start here |
+|---|---|
+| **Hobbyist** waking a Pi with your own phrase | [`docs/getting_started/quickstart.md`](docs/getting_started/quickstart.md) — ONNX in 5 minutes |
+| **Embedded engineer** shipping to ESP32 / MCU | [`docs/guides/embedded.md`](docs/guides/embedded.md) |
+| **Voice-assistant integrator** (OVOS, Rhasspy, …) | [`docs/guides/inference.md`](docs/guides/inference.md) |
+| **ML researcher** comparing architectures / losses | [`docs/guides/search.md`](docs/guides/search.md), [`docs/reference/losses.md`](docs/reference/losses.md), [`docs/research/rppl.md`](docs/research/rppl.md) |
+| **New to ML** entirely | [`docs/quickstart-kaggle.md`](docs/quickstart-kaggle.md) — step-by-step guide; runs free on Kaggle / Colab |
+
+## Highlights
+
+- **Single-string-to-ONNX** quickstart — `train_from_wakeword("hey jarvis", out)` produces a deployable model.
+- **11 built-in featurizers (+ enrichment wrappers) × 15 classifier heads × 15 losses** — a real research surface.
+- **Genetic + Bayesian HP search** with island-model parallelism, adaptive mutation, two-stage refinement.
+- **Synthetic datagen** — TTS + pure-ONNX voice conversion ([voiceclonnx](https://github.com/TigreGotico/voiceclonnx)) to bootstrap a dataset from zero recordings.
+- **Hard-negative mining** and **infinite training** for industrial-scale negative pools.
+- **ONNX-first**: featurizer and head export cleanly; no CUDA-only kernels.
+- **Hardware tiers** from `esp32_nano` (sub-1 KB int8) to `hubert_medium`.
+
+### Honest trade-offs
+
+- CPU training works for small tiers; a mid-range GPU is the best UX for larger ones.
+- Synthetic data is great for smoke-testing — production still needs real far-field recordings.
+- ONNX-export is mandatory; non-traceable components (custom CUDA kernels, dynamic control flow) are out of scope. See [`docs/internals/known_issues.md`](docs/internals/known_issues.md).
+- SSL featurizers (HuBERT, Wav2Vec2-BERT) are used as pre-exported ONNX and held frozen during downstream training — guarantees train/inference parity but limits adaptation.
+
+## Install
+
+```bash
+# Published package (import name stays ww_trainer):
+pip install --pre "wakeforge[datagen,torchcodec]"
+```
+
+For development, clone the repo and install it editable instead:
+
+```bash
+# Core library + tests
+uv pip install -e ".[dev]"
+
+# Quickstart / datagen needs TTS plugins + HF datasets + an audio codec:
+uv pip install -e ".[dev,datagen,torchcodec]"
+```
+
+Optional extras (`sweep`, `transformers`, `mlflow`, `datagen`, `vc`, `mic`,
+`viz`, `markov`, `ocsvm`, `torchcodec`) — see
+[`docs/faq.md`](docs/faq.md#2-install).
+
+A default quickstart run needs **≈ 6–8 GB disk** and **~5 GB download**
+(or ~1.5 GB with `--no-augmentation-data`). Voice cloning via `--vc-refs`
+adds the per-engine ONNX weights downloaded on first use from the
+HuggingFace Hub (size varies by `voiceclonnx` engine). Full per-dataset
+budget: [`docs/getting_started/requirements.md`](docs/getting_started/requirements.md).
+## 60-second quickstart
+
+```bash
+ww_trainer-quickstart --wake-word "hey jarvis" --output-dir ./hey_jarvis
+```
+
+Or in Python:
+
+```python
+from ww_trainer.quickstart import train_from_wakeword
+result = train_from_wakeword("hey jarvis", "./hey_jarvis",
+                             tier="small", epochs=50)
+print(result.best_onnx_path, result.metrics)
+```
+
+Output: `best_f1_featurizer.onnx` + `best_f1.onnx` under
+`./hey_jarvis/model/`. Load both with `OnnxWakeWordInferencer` —
+[`docs/guides/inference.md`](docs/guides/inference.md).
+
+## Documentation
+
+Everything lives in [`docs/`](docs/index.md). Start with:
+
+- [docs/learning_path.md](docs/learning_path.md) — **zero-to-hero curriculum** with literature anchors
+- [docs/faq.md](docs/faq.md) — topic-ordered Q&A in 15 sections
+- [docs/index.md](docs/index.md) — full documentation index
+- [examples/README.md](examples/README.md) — 43 runnable examples
+
+## Contributing
+
+Issues and pull requests welcome on the `dev` branch. Tests live in `test/`;
+run with `uv run pytest`.
+
+## Citation
+
+```bibtex
+@software{ww_trainer,
+  title  = {ww-trainer: a research suite for on-device wake-word detection},
+  author = {TigreGotico contributors},
+  year   = {2026},
+  url    = {https://github.com/TigreGotico/ww-trainer},
+  note   = {Funded by NGI0 Commons Fund / NLnet, grant 101135429}
+}
+```
+
+---
+
+## Credits
+
+Developed by [TigreGótico](https://tigregotico.pt) for
+[OpenVoiceOS](https://openvoiceos.org).
+
+[![NGI0 Commons Fund](./ngi.png)](https://nlnet.nl/project/OpenVoiceOS)
+
+This project was funded through the [NGI0 Commons Fund](https://nlnet.nl/commonsfund),
+a fund established by [NLnet](https://nlnet.nl) with financial support from the
+European Commission's [Next Generation Internet](https://ngi.eu) programme, under
+the aegis of [DG Communications Networks, Content and Technology](https://commission.europa.eu/about-european-commission/departments-and-executive-agencies/communications-networks-content-and-technology_en)
+under grant agreement No [101135429](https://cordis.europa.eu/project/id/101135429).
+
+---
+
+## License
+
+Apache 2.0

wakeforge-0.4.1a3.dist-info/RECORD

@@ -0,0 +1,47 @@
+wakeforge-0.4.1a3.dist-info/licenses/LICENSE,sha256=JBPAOkIXtKdcPVf305lJfqrNVYQ0beL0DenojOGR0EI,11346
+ww_trainer/__init__.py,sha256=e1FiyrJhPyCHzth39r_yAyqexBzNKX7nmuqvy2uNAuQ,3158
+ww_trainer/augment.py,sha256=J1PlZAQOqd1Mvgcsy2YH2XMLPhKAr7MbkocUWAL44e8,16049
+ww_trainer/benchmark.py,sha256=isqhANPg9yMT-0JriMo2992csD9fzdOeeupQOPc4oy0,27114
+ww_trainer/cache.py,sha256=dsPCNZZJbIPh5puu51ZUe_QDMNX9UeSVs7FehaqL9s8,9495
+ww_trainer/calibration.py,sha256=3zFNI2FYHxIuJ3O0i1kUSMBHk1-j7YzQ8hRGieGOeQQ,4049
+ww_trainer/checkpoint.py,sha256=1gyjl1-_lj-tJ5SrimCySNTA-zvsNnc4XlkR3v53a9s,9114
+ww_trainer/cli.py,sha256=66MvzbTri87JzRfdrO2UnboETw_Ux-upeFfXsMo6PzM,22393
+ww_trainer/datagen.py,sha256=h_BubtgsCvW7MWSYKiGtIKjIH6iQogL3r-01U94-S98,37781
+ww_trainer/dataset.py,sha256=h3GKCMdaxhSKxBKilFTbOazDbAXjoiz1q77di7tXWXI,17742
+ww_trainer/ddp.py,sha256=Qowk0YhKPk_s8XYdbhbBtz68eSzCQF9vXr-fHeWLo_Q,2948
+ww_trainer/distill.py,sha256=fN4DU83nvNt72eSk7E-oFaJ7QhU-SzQFS349WYiJ6xY,18983
+ww_trainer/env.py,sha256=-iN8X3tyvh8zJZ1bbl8etnaQgVyajM8ISY-yM8kFd0g,2505
+ww_trainer/evaluation.py,sha256=Zny-LITEvpy9Diz6PeCXNO39p_8hIF9Q7bfQvvXUSvQ,8267
+ww_trainer/export_c.py,sha256=uqBHfaeyV9Od6TISU0Kptg4QMjZtTBNUPSZwH-O20k4,5412
+ww_trainer/factory.py,sha256=urJcephjppSR0h1sp3GyaXuUsCUdGlS4P2Suj_70T0s,10252
+ww_trainer/feats.py,sha256=JzytYysddtyjBEUNafEHeqOeytoakyFoiJqtrwVgAtk,90400
+ww_trainer/few_shot.py,sha256=ZzLRtoQKnxLwFe3_DFe-gYzCd8FVbOStLNpE9B3slGE,7769
+ww_trainer/ga_mlflow.py,sha256=OLqDaqkOfbSyAW8qPADnx7bMhRwwcHbsgh8f8ntZdkM,11452
+ww_trainer/inference.py,sha256=RN9PyTnSnzoQl86W7zXoMDZJqnNQ5mOJNdQZkpoN3gA,18644
+ww_trainer/infinite_loop.py,sha256=AYfgDtxa5aPhUYjY7tE1pTB7XiAIC1f62aGvxpWy66A,24814
+ww_trainer/loop.py,sha256=6GEx4GfMCpkkE1hNflilXuB8Wz4NqclVPMgs_4qeeCM,36310
+ww_trainer/loss.py,sha256=n6VLVGFnhaM36t9xCRuaYm_suFRU4C2zPVSufBIVUTQ,60409
+ww_trainer/metrics.py,sha256=iYB3Q_SjV9yNjRGh0ShBhY0dzmwlPbh3VDgzhyPEPOY,13476
+ww_trainer/mining.py,sha256=0KxQdsA8Hpha9Ovyd3T-oAf76-uStbEwLDg0v5X0n18,7579
+ww_trainer/model.py,sha256=lIBkBRz7Mux5ikAvb46l1MHxW6KlXD1jrrM4H8Ln1yQ,67035
+ww_trainer/multi_stage.py,sha256=yY_a0PjhpgiM7VAHk_3BMKlEdlfpjpJR-PUFVcbtSec,5813
+ww_trainer/phonmatch.py,sha256=SneMTSagZj8N0UpoZ0sD0Cn8p5stwSQDuHY0HWMsLUU,18869
+ww_trainer/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ww_trainer/qat.py,sha256=CC5lV6P6KZjBGBlNkg1clK-c4LQaXO8jEc-WkDvyI-k,1942
+ww_trainer/quantize.py,sha256=lSl2lGsi5YeHOJTtbU-c5faVgW9g3x2HCSR7XgSbzNM,5113
+ww_trainer/quickstart.py,sha256=vlyF_vqYAMYAp_teyk9hECUC4vjgIrZDMwwSSilKSrk,15561
+ww_trainer/reproducibility.py,sha256=R_X0FpY2Vnqn_j3zRIjR1OMPt65DPTqmk7dUpqqjUaY,2610
+ww_trainer/subspectralnorm.py,sha256=x-jOB-t7crLUStZXx5M9uxbaYCIdF_IOk-gKDWGzhsI,2590
+ww_trainer/sweep.py,sha256=wM_S_XqOmTa-vZKlGMMahVbnz7fETCkwXZwW0d06yJ4,51752
+ww_trainer/tiers.py,sha256=64TLPQYhvRRzbeR6uRWBWilNhWBA_CDpQDV0MwMp3bI,7135
+ww_trainer/trainer.py,sha256=MKRB_t2wLDOlRom7wUzdqb23yh325fiIgwH2iJTiNjY,12880
+ww_trainer/utils.py,sha256=6p7gdd_U_tFdTQHekWIdH7gdYRPiitd98rJDf5ElOMA,12848
+ww_trainer/vc_helpers.py,sha256=qVNRrczq704FOOvTTK_VIvWxkVK8D25-HVXBTow3zNE,4711
+ww_trainer/version.py,sha256=t0E7Cilboqm6hhWpfxdxeAS4JzPFBCvSJkHnE1lBIzs,281
+ww_trainer/visualization.py,sha256=A_c4ZoZJMZkeh-8rWBAJMVys5WHsp-RUPkc_14025Wg,36527
+ww_trainer/vendors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+wakeforge-0.4.1a3.dist-info/METADATA,sha256=XIWugkJxIIcpUmEp0p1pjaaRQ16o90_dpKiKqRDB2H4,8632
+wakeforge-0.4.1a3.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
+wakeforge-0.4.1a3.dist-info/entry_points.txt,sha256=7az86R-oTxIWsafo8j1b76dOkgJu-zwRf4HfX6U0dHo,260
+wakeforge-0.4.1a3.dist-info/top_level.txt,sha256=B0jBNzFa__yFDLk2N39wmyj6uoQwAnWrI266fkKBwqE,11
+wakeforge-0.4.1a3.dist-info/RECORD,,

wakeforge-0.4.1a3.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.0.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

wakeforge-0.4.1a3.dist-info/entry_points.txt

@@ -0,0 +1,6 @@
+[console_scripts]
+ww_trainer-benchmark = ww_trainer.benchmark:main
+ww_trainer-datagen = ww_trainer.datagen:cli_main
+ww_trainer-infer = ww_trainer.inference:cli_main
+ww_trainer-quickstart = ww_trainer.quickstart:cli_main
+ww_trainer-train = ww_trainer.cli:train

wakeforge-0.4.1a3.dist-info/licenses/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.

wakeforge-0.4.1a3.dist-info/top_level.txt

@@ -0,0 +1 @@
+ww_trainer

ww_trainer/__init__.py

@@ -0,0 +1,139 @@
+"""ww-trainer: Full training and research suite for wake words.
+
+All exported to ONNX — from MFCC on microcontrollers to HuBERT on servers.
+"""
+from ww_trainer.version import __version__
+
+# --- Feature Extractors ---
+from ww_trainer.feats import (
+    BaseExtractor,
+    OnnxFeatureExtractor,
+    MfccExtractor,
+    FilterbankExtractor,
+    SincNetExtractor,
+    GammatoneExtractor,
+    DeltaExtractor,
+    LEAFExtractor,
+    PLPExtractor,
+    PNCCExtractor,
+    CQTExtractor,
+    VoiceActivityExtractor,
+    PitchExtractor,
+    MultiResolutionExtractor,
+    SNRAwareExtractor,
+    SlidingFeatureCacheTensor,
+    MarkovTransitionExtractor,
+    HMMStateExtractor,
+    OnnxTextExtractor,
+)
+
+# --- Classifier Heads ---
+from ww_trainer.model import (
+    ClassifierHead,
+    BaseWakeModel,
+    FfnClassifierHead,
+    CnnClassifierHead,
+    GruClassifierHead,
+    BCResNetHead,
+    TCResNetHead,
+    DSCNNHead,
+    MatchboxNetHead,
+    Res15Head,
+    KWTHead,
+    ConformerHead,
+    CRNNHead,
+    AttentionPooling,
+    ConvAttentionHead,
+)
+
+# --- Losses ---
+from ww_trainer.loss import (
+    LossManager,
+    FocalLoss,
+    LabelSmoothingBCE,
+    ArcFaceLoss,
+    CenterLoss,
+    NTXentLoss,
+    SupConLoss,
+    ProxyNCALoss,
+    MultiSimilarityLoss,
+    ContrastiveLoss,
+    LiftedStructureLoss,
+    AngularLoss,
+    SoftTripletLoss,
+    CN2Plus1PairLoss,
+    RobustProtoDiversityLoss,
+)
+
+# --- Inference ---
+from ww_trainer.inference import OnnxWakeWordInferencer, OnnxStreamingWakeWord
+
+# --- Dataset ---
+from ww_trainer.dataset import AudioDataset, collate_fn
+
+# --- Tiers ---
+from ww_trainer.tiers import HARDWARE_TIERS, TierConfig
+
+# --- PhonMatchNet text encoder + cross-attention head ---
+from ww_trainer.phonmatch import (
+    IPA_VOCAB,
+    ARPABET_TO_IPA,
+    PHONEME_VOCAB,   # alias for IPA_VOCAB — backward compat
+    VOCAB_SIZE,
+    ipa_to_ids,
+    arpabet_to_ids,
+    phonemes_to_ids,  # alias for arpabet_to_ids — backward compat
+    PhonMatchTextEncoder,
+    PhonMatchHead,
+)
+
+# --- Distillation ---
+from ww_trainer.distill import CnnLstmExtractor, KnowledgeDistillationTrainer
+
+# --- Metrics ---
+from ww_trainer.metrics import (
+    DetectionReport,
+    compute_eer,
+    compute_far_frr,
+    find_optimal_threshold,
+    det_curve,
+    area_under_det,
+    classification_report,
+)
+
+# --- Checkpoint helpers ---
+from ww_trainer.checkpoint import (
+    save_checkpoint,
+    average_checkpoints,
+    select_best_checkpoints,
+)
+
+# --- Factory ---
+from ww_trainer.factory import (
+    create_model, EXTRACTOR_REGISTRY, HEAD_REGISTRY,
+    register_extractor, register_head,
+)
+
+# --- Evaluation ---
+from ww_trainer.evaluation import evaluate_model, evaluate_detection, log_metrics_csv
+
+# --- Quantization ---
+from ww_trainer.quantize import quantize_onnx, quantize_model_pair, QuantizationReport
+
+# --- Reproducibility ---
+from ww_trainer.reproducibility import set_seed, get_seed_info
+
+# --- Augmentation ---
+from ww_trainer.augment import (
+    AugmentationPipeline,
+    AudioTransform,
+    MixBackground,
+    ApplyReverb,
+    PitchShift,
+    SpeedPerturb,
+    GaussianNoise,
+    VolumePerturb,
+    TimeShift,
+    SpecAugment,
+    Normalize,
+)