naptrap 0.1.0__tar.gz

naptrap-0.1.0/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 [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.

naptrap-0.1.0/MANIFEST.in

@@ -0,0 +1,4 @@
+include README.md LICENSE NOTICE THIRD_PARTY_NOTICES.md
+recursive-include docs *.md
+recursive-include licenses *.txt
+recursive-include tests *.py

naptrap-0.1.0/NOTICE

@@ -0,0 +1,19 @@
+naptrap
+Copyright 2026 Drew Bednar
+
+This product is licensed under the Apache License, Version 2.0 (LICENSE).
+
+src/naptrap/models/network.py implements the PhonMatchNet architecture
+(Yong-Hyeok Lee and Namhyun Cho, Interspeech 2023) after NCSOFT's
+BSD-3-Clause PyTorch implementation, https://github.com/ncsoft/PhonMatchNet.
+NCSOFT's copyright notice and license: licenses/PhonMatchNet-BSD-3-Clause.txt.
+naptrap is not affiliated with or endorsed by NCSOFT or the PhonMatchNet authors.
+
+src/naptrap/text.py reimplements the decoder-state "embedding" computation of
+g2p_en by Kyubyong Park and Jongseok Kim (Apache-2.0),
+https://github.com/Kyubyong/g2p.
+
+src/naptrap/google.py reimplements Google's speech_embedding/1 model
+(Apache-2.0) in PyTorch. naptrap is not affiliated with or endorsed by Google.
+
+Model weights are not included in this package; see THIRD_PARTY_NOTICES.md.

naptrap-0.1.0/PKG-INFO

@@ -0,0 +1,213 @@
+Metadata-Version: 2.4
+Name: naptrap
+Version: 0.1.0
+Summary: Local, text-defined wake word and keyword detection in PyTorch
+Author-email: Drew Bednar <drew@runcible.io>
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/androiddrew/naptrap
+Project-URL: Issues, https://github.com/androiddrew/naptrap/issues
+Project-URL: Models, https://huggingface.co/androiddrew/naptrap-phonmatchnet-en
+Keywords: wake word,keyword spotting,speech,phonmatchnet,pytorch,kws
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+License-File: licenses/PhonMatchNet-BSD-3-Clause.txt
+Requires-Dist: torch>=1.13
+Requires-Dist: safetensors>=0.4
+Provides-Extra: hub
+Requires-Dist: huggingface_hub>=0.20; extra == "hub"
+Provides-Extra: test
+Requires-Dist: pytest>=7; extra == "test"
+Requires-Dist: numpy; extra == "test"
+Dynamic: license-file
+
+# naptrap
+
+**Local, text-defined wake word detection in PyTorch.** Type a keyword, give
+naptrap a short audio clip, and it tells you whether the keyword was spoken.
+New wake words need no recordings or training.
+
+```python
+from naptrap import load_model, load_wav
+
+model = load_model("phonmatchnet")             # downloads the model on first use
+result = model.detect(load_wav("clip.wav"), "hey computer")
+
+print(result.score)     # keyword-match probability, 0-1
+print(result.accepted)  # score >= the model's calibrated threshold
+```
+
+The first model is an independently trained
+[PhonMatchNet](https://huggingface.co/androiddrew/naptrap-phonmatchnet-en)
+(Lee & Cho, Interspeech 2023) for English. Inference runs on the CPU with
+**PyTorch as the only heavy dependency**. There is no TensorFlow, NumPy,
+torchaudio or NLTK, and no cloud API.
+
+## Install
+
+```bash
+pip install "naptrap[hub]"
+```
+
+Python 3.9+ and PyTorch 1.13+ are required. If you want a CPU-only or
+CUDA-specific PyTorch build, install it first; see
+[pytorch.org](https://pytorch.org/get-started/locally/). The `hub` extra adds
+`huggingface_hub` for automatic model downloads. Without it, `pip install
+naptrap` works with model directories you download yourself.
+
+## Models
+
+`load_model("phonmatchnet")` fetches three Hugging Face repositories (about
+6 MB in total), pinned to revision `v1`, and caches them locally:
+
+| Repository | Role | License |
+|---|---|---|
+| [`androiddrew/naptrap-phonmatchnet-en`](https://huggingface.co/androiddrew/naptrap-phonmatchnet-en) | keyword matcher | Apache-2.0 |
+| [`androiddrew/google-speech-embedding-pytorch`](https://huggingface.co/androiddrew/google-speech-embedding-pytorch) | frozen audio encoder | Apache-2.0 |
+| [`androiddrew/g2p-en-decoder-pytorch`](https://huggingface.co/androiddrew/g2p-en-decoder-pytorch) | frozen keyword text encoder | Apache-2.0 |
+
+To work offline, download them once and pass the directories:
+
+```bash
+hf download androiddrew/naptrap-phonmatchnet-en --revision v1 --local-dir models/phonmatchnet
+hf download androiddrew/google-speech-embedding-pytorch --revision v1 --local-dir models/google
+hf download androiddrew/g2p-en-decoder-pytorch --revision v1 --local-dir models/g2p
+```
+
+```python
+model = load_model("phonmatchnet", model_dir="models/phonmatchnet",
+                   google_dir="models/google", g2p_dir="models/g2p")
+```
+
+Every weight file is checked against the SHA-256 recorded in its `config.json`.
+The keyword model also pins the exact encoders it was trained with.
+
+## Usage
+
+### Audio
+
+`detect()` scores **one mono 16 kHz clip of 0.5–2 seconds**, given as a 1-D
+float32 tensor or array with values in [-1, 1]. `load_wav()` reads 16-bit PCM
+WAV files using only the standard library. Convert other files first:
+
+```bash
+ffmpeg -i input.m4a -ac 1 -ar 16000 -sample_fmt s16 clip.wav
+```
+
+naptrap does not resample, trim or rescale audio for you.
+
+### Reusing a keyword
+
+Converting the keyword text is cheap, but if you score many clips against the
+same keyword you can do it once:
+
+```python
+wake = model.keyword("hey computer")
+for clip in clips:
+    if model.detect(clip, wake).accepted:
+        ...
+```
+
+Keywords are English words; accents and punctuation are removed. Spell out
+numbers ("route sixty six").
+
+### Operating points and thresholds
+
+```python
+model.thresholds                                # {0.01: 0.7149..., 0.1: 0.0025...}
+model.detect(clip, "hey computer", far=0.1)     # more sensitive
+```
+
+Each threshold was fitted on held-out development speakers to target a
+per-clip false-accept rate (FAR) of 1% or 10%. **These targets do not hold on
+other audio.** On phonetically confusable phrases, the 1% threshold accepted
+31% of negatives. For a real product, record some positive and negative clips
+in your setting and choose your own threshold on `result.score`. See the
+[model card](https://huggingface.co/androiddrew/naptrap-phonmatchnet-en) for
+the evaluation.
+
+### Command line
+
+```bash
+naptrap detect clip.wav "hey computer"
+naptrap detect clip.wav "hey computer" --far 0.1 --model-dir models/phonmatchnet \
+    --google-dir models/google --g2p-dir models/g2p
+```
+
+The command prints the prediction as JSON. It exits with 0 if the keyword was
+accepted, 1 if it was rejected and 2 on error. `python -m naptrap` works the
+same way.
+
+### Precomputed features
+
+`model.predict({"keyword_mel": ..., "google": ..., "text": ...})` scores
+features you computed yourself: `[T, 40]`, `[T/8, 96]` and `[P, 256]` float32.
+The encoders are exposed as `naptrap.GoogleSpeechEmbedding` and
+`naptrap.G2PTextEncoder`.
+
+## Limitations
+
+- **Single clips, not a streaming listener (yet).** To watch a microphone you
+  must window the audio yourself, e.g. 1.5 s windows every 0.25 s, and add
+  your own debouncing.
+- **English only**, trained on read audiobook speech (LibriSpeech). Expect
+  lower accuracy with noise, far-field microphones, accents or children.
+- **No speaker verification.** Anyone saying the keyword triggers it.
+- Similar-sounding phrases are often confused.
+- CPU inference is the supported path; other devices have not been validated.
+- Not for security or safety-critical use.
+
+## Adding model families
+
+Backends implement `keyword()`, `detect()` and `predict()`, and return a
+`Prediction`. Register a loader under a new name:
+
+```python
+from naptrap import register_model, load_model
+
+register_model("my-model", MyModel.from_pretrained)
+model = load_model("my-model", model_dir="...")
+```
+
+## Development
+
+```bash
+pip install -e ".[test]"
+pytest
+# Also run the real-model tests against downloaded model directories:
+NAPTRAP_TEST_MODELS=path/to/models pytest
+```
+
+`NAPTRAP_TEST_MODELS` must point at a directory holding the three model
+repositories in subdirectories named `naptrap-phonmatchnet-en`,
+`google-speech-embedding-pytorch` and `g2p-en-decoder-pytorch`.
+
+## License and attribution
+
+naptrap is licensed under the [Apache License 2.0](LICENSE). The network
+follows the PhonMatchNet design and NCSOFT's BSD-3-Clause reference code (see
+[NOTICE](NOTICE) and [licenses/](licenses/)). The PhonMatchNet weights were
+trained independently. **naptrap is not affiliated with or endorsed by NCSOFT
+or the PhonMatchNet authors.** See
+[THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md) for every component.
+
+If naptrap's PhonMatchNet model is useful in your research, please cite:
+
+```bibtex
+@inproceedings{lee23phonmatchnet,
+  title     = {PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spotting for User-Defined Keywords},
+  author    = {Lee, Yong-Hyeok and Cho, Namhyun},
+  booktitle = {Proc. INTERSPEECH 2023},
+  pages     = {3964--3968},
+  year      = {2023}
+}
+```

naptrap-0.1.0/README.md

@@ -0,0 +1,181 @@
+# naptrap
+
+**Local, text-defined wake word detection in PyTorch.** Type a keyword, give
+naptrap a short audio clip, and it tells you whether the keyword was spoken.
+New wake words need no recordings or training.
+
+```python
+from naptrap import load_model, load_wav
+
+model = load_model("phonmatchnet")             # downloads the model on first use
+result = model.detect(load_wav("clip.wav"), "hey computer")
+
+print(result.score)     # keyword-match probability, 0-1
+print(result.accepted)  # score >= the model's calibrated threshold
+```
+
+The first model is an independently trained
+[PhonMatchNet](https://huggingface.co/androiddrew/naptrap-phonmatchnet-en)
+(Lee & Cho, Interspeech 2023) for English. Inference runs on the CPU with
+**PyTorch as the only heavy dependency**. There is no TensorFlow, NumPy,
+torchaudio or NLTK, and no cloud API.
+
+## Install
+
+```bash
+pip install "naptrap[hub]"
+```
+
+Python 3.9+ and PyTorch 1.13+ are required. If you want a CPU-only or
+CUDA-specific PyTorch build, install it first; see
+[pytorch.org](https://pytorch.org/get-started/locally/). The `hub` extra adds
+`huggingface_hub` for automatic model downloads. Without it, `pip install
+naptrap` works with model directories you download yourself.
+
+## Models
+
+`load_model("phonmatchnet")` fetches three Hugging Face repositories (about
+6 MB in total), pinned to revision `v1`, and caches them locally:
+
+| Repository | Role | License |
+|---|---|---|
+| [`androiddrew/naptrap-phonmatchnet-en`](https://huggingface.co/androiddrew/naptrap-phonmatchnet-en) | keyword matcher | Apache-2.0 |
+| [`androiddrew/google-speech-embedding-pytorch`](https://huggingface.co/androiddrew/google-speech-embedding-pytorch) | frozen audio encoder | Apache-2.0 |
+| [`androiddrew/g2p-en-decoder-pytorch`](https://huggingface.co/androiddrew/g2p-en-decoder-pytorch) | frozen keyword text encoder | Apache-2.0 |
+
+To work offline, download them once and pass the directories:
+
+```bash
+hf download androiddrew/naptrap-phonmatchnet-en --revision v1 --local-dir models/phonmatchnet
+hf download androiddrew/google-speech-embedding-pytorch --revision v1 --local-dir models/google
+hf download androiddrew/g2p-en-decoder-pytorch --revision v1 --local-dir models/g2p
+```
+
+```python
+model = load_model("phonmatchnet", model_dir="models/phonmatchnet",
+                   google_dir="models/google", g2p_dir="models/g2p")
+```
+
+Every weight file is checked against the SHA-256 recorded in its `config.json`.
+The keyword model also pins the exact encoders it was trained with.
+
+## Usage
+
+### Audio
+
+`detect()` scores **one mono 16 kHz clip of 0.5–2 seconds**, given as a 1-D
+float32 tensor or array with values in [-1, 1]. `load_wav()` reads 16-bit PCM
+WAV files using only the standard library. Convert other files first:
+
+```bash
+ffmpeg -i input.m4a -ac 1 -ar 16000 -sample_fmt s16 clip.wav
+```
+
+naptrap does not resample, trim or rescale audio for you.
+
+### Reusing a keyword
+
+Converting the keyword text is cheap, but if you score many clips against the
+same keyword you can do it once:
+
+```python
+wake = model.keyword("hey computer")
+for clip in clips:
+    if model.detect(clip, wake).accepted:
+        ...
+```
+
+Keywords are English words; accents and punctuation are removed. Spell out
+numbers ("route sixty six").
+
+### Operating points and thresholds
+
+```python
+model.thresholds                                # {0.01: 0.7149..., 0.1: 0.0025...}
+model.detect(clip, "hey computer", far=0.1)     # more sensitive
+```
+
+Each threshold was fitted on held-out development speakers to target a
+per-clip false-accept rate (FAR) of 1% or 10%. **These targets do not hold on
+other audio.** On phonetically confusable phrases, the 1% threshold accepted
+31% of negatives. For a real product, record some positive and negative clips
+in your setting and choose your own threshold on `result.score`. See the
+[model card](https://huggingface.co/androiddrew/naptrap-phonmatchnet-en) for
+the evaluation.
+
+### Command line
+
+```bash
+naptrap detect clip.wav "hey computer"
+naptrap detect clip.wav "hey computer" --far 0.1 --model-dir models/phonmatchnet \
+    --google-dir models/google --g2p-dir models/g2p
+```
+
+The command prints the prediction as JSON. It exits with 0 if the keyword was
+accepted, 1 if it was rejected and 2 on error. `python -m naptrap` works the
+same way.
+
+### Precomputed features
+
+`model.predict({"keyword_mel": ..., "google": ..., "text": ...})` scores
+features you computed yourself: `[T, 40]`, `[T/8, 96]` and `[P, 256]` float32.
+The encoders are exposed as `naptrap.GoogleSpeechEmbedding` and
+`naptrap.G2PTextEncoder`.
+
+## Limitations
+
+- **Single clips, not a streaming listener (yet).** To watch a microphone you
+  must window the audio yourself, e.g. 1.5 s windows every 0.25 s, and add
+  your own debouncing.
+- **English only**, trained on read audiobook speech (LibriSpeech). Expect
+  lower accuracy with noise, far-field microphones, accents or children.
+- **No speaker verification.** Anyone saying the keyword triggers it.
+- Similar-sounding phrases are often confused.
+- CPU inference is the supported path; other devices have not been validated.
+- Not for security or safety-critical use.
+
+## Adding model families
+
+Backends implement `keyword()`, `detect()` and `predict()`, and return a
+`Prediction`. Register a loader under a new name:
+
+```python
+from naptrap import register_model, load_model
+
+register_model("my-model", MyModel.from_pretrained)
+model = load_model("my-model", model_dir="...")
+```
+
+## Development
+
+```bash
+pip install -e ".[test]"
+pytest
+# Also run the real-model tests against downloaded model directories:
+NAPTRAP_TEST_MODELS=path/to/models pytest
+```
+
+`NAPTRAP_TEST_MODELS` must point at a directory holding the three model
+repositories in subdirectories named `naptrap-phonmatchnet-en`,
+`google-speech-embedding-pytorch` and `g2p-en-decoder-pytorch`.
+
+## License and attribution
+
+naptrap is licensed under the [Apache License 2.0](LICENSE). The network
+follows the PhonMatchNet design and NCSOFT's BSD-3-Clause reference code (see
+[NOTICE](NOTICE) and [licenses/](licenses/)). The PhonMatchNet weights were
+trained independently. **naptrap is not affiliated with or endorsed by NCSOFT
+or the PhonMatchNet authors.** See
+[THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md) for every component.
+
+If naptrap's PhonMatchNet model is useful in your research, please cite:
+
+```bibtex
+@inproceedings{lee23phonmatchnet,
+  title     = {PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spotting for User-Defined Keywords},
+  author    = {Lee, Yong-Hyeok and Cho, Namhyun},
+  booktitle = {Proc. INTERSPEECH 2023},
+  pages     = {3964--3968},
+  year      = {2023}
+}
+```

naptrap-0.1.0/THIRD_PARTY_NOTICES.md

@@ -0,0 +1,17 @@
+# Third-party notices
+
+naptrap's own code is licensed under Apache-2.0 (see `LICENSE` and `NOTICE`).
+The package bundles **no model weights**. Weights are downloaded separately
+from Hugging Face, and each repository carries its own license and notices.
+
+| Component | Used for | License | Where |
+|---|---|---|---|
+| PhonMatchNet architecture and training code, © NCSOFT Corporation | `naptrap/models/network.py` follows its network design | BSD-3-Clause | `licenses/PhonMatchNet-BSD-3-Clause.txt`, <https://github.com/ncsoft/PhonMatchNet> |
+| PhonMatchNet weights, trained independently by Drew Bednar | default keyword model | Apache-2.0 | <https://huggingface.co/androiddrew/naptrap-phonmatchnet-en> |
+| Google speech_embedding/1 | frozen audio features (`naptrap/google.py`) | Apache-2.0 | <https://huggingface.co/androiddrew/google-speech-embedding-pytorch> |
+| g2p_en 2.1.0, Kyubyong Park & Jongseok Kim | frozen keyword text features (`naptrap/text.py`) | Apache-2.0 | <https://huggingface.co/androiddrew/g2p-en-decoder-pytorch> |
+| LibriSpeech (Panayotov et al.) | training data for the PhonMatchNet weights | CC BY 4.0 | <https://www.openslr.org/12> |
+| PyTorch, safetensors, huggingface_hub (optional) | runtime dependencies, installed separately | BSD-3-Clause / Apache-2.0 / Apache-2.0 | PyPI |
+
+naptrap and these weights are not affiliated with or endorsed by NCSOFT, the
+PhonMatchNet authors, Google or the g2p_en authors.

naptrap-0.1.0/docs/compatibility.md

@@ -0,0 +1,24 @@
+# Compatibility
+
+naptrap requires Python 3.9+, PyTorch 1.13+ and safetensors 0.4+. There are
+no upper version pins. The library uses eager PyTorch modules only (no
+TorchScript) and standard convolution, GRU and FFT operations.
+
+The full test suite, including the released-model checks, passes on CPU with:
+
+| Python | PyTorch | safetensors |
+|---|---|---|
+| 3.9 | 1.13.1 | 0.7 |
+| 3.12 | 2.14.1 | 0.8 |
+| 3.13 | 2.14.1 | 0.8 |
+
+Any Python version with a PyTorch wheel for your platform should work.
+Inference runs on the CPU. Scoring a 1.5 s clip takes about 7 ms using two
+threads of a desktop CPU; converting a keyword takes about 2 ms.
+
+NumPy is not required. `load_wav()` uses the standard library, and NumPy
+arrays are accepted as inputs if you already have them.
+
+The test extra installs NumPy, which safetensors needs to write the test
+fixtures. With PyTorch < 2.3, use NumPy 1.x to avoid a harmless NumPy-ABI
+warning.