paradis-tts 0.1.1__tar.gz

paradis_tts-0.1.1/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.

paradis_tts-0.1.1/MANIFEST.in

@@ -0,0 +1,9 @@
+include README.md LICENSE NOTICE pyproject.toml
+include paradis_tts/release_assets.json
+prune tests
+include tests/test_public_api.py
+exclude paradis_tts/inference.py
+exclude paradis_tts/onnx_models.py
+exclude paradis_tts/fricative_probe.py
+exclude paradis_tts/softening_probe.py
+exclude paradis_tts/phase_filter_probe.py

paradis_tts-0.1.1/NOTICE

@@ -0,0 +1,87 @@
+Paradis-TTS — provenance notices
+
+paradis_tts/onnx_models.py adapts the single-sentence text forward and
+convolutional STFT from Paradee training/scripts/export_paradee.py,
+Sahil Mahendrakar, commit 9c8b4d7504cbee7e64de2d0341bb690f0b0ab708,
+Apache-2.0. Changes: French A_full_phase, three explicit deterministic ONNX
+stages, host excitation and host postprocessing, CPU parity checks and
+portable FP32/INT8-weight bundles. See LICENSE and docs/PHASE9_ONNX.md.
+
+The portable NumPy phase filter in paradis_tts/audio.py implements the same
+Paradee relative-phase correction described below; existing training sources
+and their licenses are unchanged.
+
+Paradis-TTS — phase 0 French feasibility audit
+
+The teacher extraction in scripts/test_teacher_fr.py is adapted from:
+Paradee, Sahil Mahendrakar
+https://github.com/sahilmahendrakar/paradee
+Commit: 9c8b4d7504cbee7e64de2d0341bb690f0b0ab708
+File: training/scripts/gen_teacher.py
+License: Apache-2.0 (see LICENSE)
+Changes: French ff_siwis, pinned assets, CPU determinism, strict vocabulary
+validation, hooks for independent parity checks, logs and test artifacts.
+
+Kokoro-82M and Kokoro / Misaki software: hexgrad, Apache-2.0.
+https://huggingface.co/hexgrad/Kokoro-82M
+https://github.com/hexgrad/kokoro
+https://github.com/hexgrad/misaki
+
+French teacher voice: ff_siwis. Kokoro attributes its source data to:
+Yamagishi, Junichi; Honnet, Pierre-Edouard; Garner, Philip; Lazaridis, Alexandros.
+(2017). The SIWIS French Speech Synthesis Database, 2016 [dataset].
+University of Edinburgh, School of Informatics, Centre for Speech Technology Research.
+https://doi.org/10.7488/ds/1705
+Source-data license: https://creativecommons.org/licenses/by/4.0/
+The included WAVs are synthetic Kokoro outputs from original test sentences;
+they are not recordings downloaded from SIWIS.
+
+No WikiText or Wikipedia text is redistributed in phase 0 evidence.
+Phase 1 includes French Wikipedia sentence excerpts in data/:
+Contributors to French Wikipedia; article and history URLs in metadata.jsonl.
+Source: wikimedia/wikipedia, 20231101.fr,
+revision b04c8d1ceb2f5cd4588862100d08de323dccfbaa.
+Original source-declared license: CC BY-SA 3.0.
+Adapted corpus / original coverage sentences: CC BY-SA 4.0.
+See data/README.md and docs/LICENSING.md for notices and changes.
+
+Phase 2 extraction adapts Paradee training/scripts/gen_teacher.py and
+training/scripts/regen_audio.py at the same audited Paradee commit.
+Changes include French corpus/voice, stable per-ID seeds, atomic tensor shards,
+checked resume, and a CUDA decoder with original CPU excitation and FFT math.
+Generated teacher audio is kept in tensor shards without additional WAV exports.
+Dependency licenses, including eSpeak NG's GPL, remain separate from this
+repository's source-code license; see docs/LICENSING.md.
+
+Phases 3/4 include unmodified Paradee training/scripts/student.py and
+student_decoder.py in training/vendor/, under Apache-2.0 at the audited commit.
+training/batches.py and losses.py adapt its baseline collators and loss formulas.
+Changes: French split-aware smoke subsets, deterministic CPU reflection padding,
+small batches/accumulation, portable RNG/optimizer/scaler checkpoints and Colab tools.
+No English Paradee model weights or English corpus are used for French training.
+
+Phase 6 includes unmodified Paradee training/scripts/discriminators.py at the
+same audited commit. training/decoder_training.py and decoder_gan.py adapt
+train_decoder.py: French split-aware data, spectral/GAN stages, CPU reflection
+padding, exact global STFT convergence across accumulated microbatches, full
+optimizer/discriminator/RNG resume, Drive backups and tensor/HTML listening.
+
+paradis_tts/phase_lock.py adapts Paradee training/scripts/phase_lock.py at the
+same audited Apache-2.0 commit. It is initially exposed in a CPU listening A/B
+test; the raw student inference and trained checkpoints remain the references.
+tests/fixtures/upstream_phase_lock.py contains the original smooth/lock
+function bodies for a standalone parity test, under the same Apache-2.0 license.
+
+The optional high-frequency loss in training/decoder_hf.py adapts the
+--hf-weight objective from Paradee training/scripts/train_decoder.py at
+commit 9c8b4d7504cbee7e64de2d0341bb690f0b0ab708 (Apache-2.0).
+Evaluation uses the non-personalized DNSMOS P.835 windowing/calibration method
+from Microsoft DNS-Challenge, revision 591184a9fcb2cbdec02520fed81a32bbbf9d73ff,
+DNSMOS/dnsmos_local.py. Source repository license: CC BY 4.0.
+https://github.com/microsoft/DNS-Challenge
+https://creativecommons.org/licenses/by/4.0/
+Adaptation: P.835 only (no P.808), SciPy polyphase resampling, explicit CPU thread
+limits, resumable per-sentence logs and integration with held-out TTS evaluation.
+DNSMOS model files are downloaded for evaluation and are not redistributed in
+the Python package or inference archives. This attribution does not imply
+Microsoft endorses Paradis-TTS.

paradis_tts-0.1.1/PKG-INFO

@@ -0,0 +1,127 @@
+Metadata-Version: 2.4
+Name: paradis-tts
+Version: 0.1.1
+Summary: Compact French text-to-speech on CPU, with built-in audio postprocessing
+Author: IvannP39
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/IvannP39/Paradis-TTS-release
+Project-URL: Models, https://huggingface.co/IvannP/Paradis-TTS
+Project-URL: Issues, https://github.com/IvannP39/Paradis-TTS-release/issues
+Keywords: tts,french,onnx,speech-synthesis,offline
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Natural Language :: French
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Requires-Python: <3.13,>=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: numpy<2,>=1.26.4
+Requires-Dist: onnxruntime<1.21,>=1.20.1
+Requires-Dist: misaki==0.9.4
+Requires-Dist: num2words==0.5.14
+Requires-Dist: phonemizer-fork==3.3.2
+Requires-Dist: espeakng-loader==0.2.4
+Dynamic: license-file
+
+<p align="center"><img src="https://raw.githubusercontent.com/IvannP39/Paradis-TTS-release/main/assets/paradis-banner.png" alt="Paradis — Synthèse vocale française sur CPU" width="100%"></p>
+
+<p align="center">
+  <a href="https://github.com/IvannP39/Paradis-TTS-release/releases/tag/v0"><img alt="Release v0" src="https://img.shields.io/badge/release-v0-9ee8cb?style=flat-square"></a>
+  <a href="https://huggingface.co/IvannP/Paradis-TTS"><img alt="Hugging Face" src="https://img.shields.io/badge/Hugging_Face-mod%C3%A8les-ffd681?style=flat-square"></a>
+  <img alt="CPU et ONNX" src="https://img.shields.io/badge/runtime-CPU_%C2%B7_ONNX-c3dbe6?style=flat-square">
+  <a href="https://github.com/IvannP39/Paradis-TTS-release/blob/main/LICENSE"><img alt="Apache 2.0" src="https://img.shields.io/badge/code_%26_poids-Apache_2.0-c3dbe6?style=flat-square"></a>
+</p>
+
+**Une voix française compacte, directement dans votre application.**
+Paradis-TTS transforme du texte en audio sur CPU, avec 8,08 millions de paramètres,
+des poids ONNX FP32 ou INT8, et un post-traitement intégré. Après le premier
+téléchargement, la synthèse fonctionne entièrement hors ligne.
+
+[Écouter la voix](https://huggingface.co/IvannP/Paradis-TTS#écouter) ·
+[Télécharger v0](https://github.com/IvannP39/Paradis-TTS-release/releases/tag/v0) ·
+[Documentation Python](https://github.com/IvannP39/Paradis-TTS-release/blob/main/docs/PYTHON_PACKAGE.md)
+
+## Essayer
+
+Python 3.10–3.12. Installer le wheel public :
+
+```bash
+python -m pip install https://github.com/IvannP39/Paradis-TTS-release/releases/download/v0/paradis_tts-0.1.1-py3-none-any.whl
+```
+
+```python
+from paradis_tts import ParadisTTS
+
+tts = ParadisTTS()
+audio = tts("Bonjour tout le monde.")
+tts.save(audio, "bonjour.wav")
+```
+
+La construction de `ParadisTTS()` télécharge les poids FP32 depuis Hugging Face
+et les garde en cache après vérification SHA256. Aucun GPU, PyTorch ni
+Kokoro n'est nécessaire. `audio` est un tableau NumPy mono, `float32`, à 24 kHz.
+Le package est prêt pour PyPI ; l'installation ci-dessus utilise la release
+GitHub et ne suppose pas une publication dans l'index PyPI.
+
+## Choisir sa version
+
+| | FP32 | INT8 |
+|---|---:|---:|
+| Archive à télécharger | 30.21 Mo | 8.21 Mo |
+| Trois graphes ONNX | 32,82 Mo | 9,19 Mo |
+| Paramètres | 8 082 881 | 8 082 881 |
+| Poids | Flottants | Entiers 8 bits, déquantifiés au calcul |
+
+```python
+tts = ParadisTTS(variant="int8")
+tts = ParadisTTS(post_traitement=False)  # sortie brute
+tts = ParadisTTS(model_folder="chemin/vers/fp32")  # archive locale décompressée
+```
+
+Le profil audio par défaut associe le filtre de phase 97, une restauration de
+présence jusqu'à 2,5 dB et deux adoucissements du spectre à 1 et 1,5 dB.
+[Réglages et usage hors ligne](https://github.com/IvannP39/Paradis-TTS-release/blob/main/docs/PYTHON_PACKAGE.md).
+L'INT8 réduit le téléchargement ; il ne garantit pas une exécution plus rapide
+et peut modifier la voix. Le FP32 est le choix par défaut.
+
+## Mesures v0
+
+300 phrases inédites, articles séparés du corpus de distillation. CPU AMD Ryzen 7 5800H, Windows, deux threads configurés dans ONNX Runtime/PyTorch.
+
+| Moteur | WER ↓ | DNSMOS global ↑ | RTF médian ↓ | Pic RSS |
+|---|---:|---:|---:|---:|
+| Paradis FP32 | 12.51 % | 3.36 | 0.175 | 374 Mio |
+| Paradis INT8 | 12.70 % | 3.35 | 0.183 | 355 Mio |
+| Kokoro ff_siwis | 12.33 % | 3.42 | 0.719 | 4405 Mio |
+| Piper siwis medium | 16.47 % | 3.25 | 0.119 | 497 Mio |
+
+WER : taux d’erreurs de mots mesuré par Whisper Small en français. DNSMOS P.835 est un proxy parole/bruit, **pas une note d’écoute humaine ni une mesure suffisante de naturalité**. RTF < 1 signifie une génération plus rapide que la lecture. Les mesures ont eu lieu sur un portable partagé avec un entraînement GPU et d’autres tâches CPU ; elles ne constituent pas un classement en conditions isolées. [Protocole, scores par phrase et limites](https://github.com/IvannP39/Paradis-TTS-release/tree/main/evaluation).
+
+## D'où vient la voix ?
+
+Paradis adapte la méthode de [Paradee](https://github.com/sahilmahendrakar/paradee)
+au français et distille [Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M),
+voix `ff_siwis`. Cette v0 assemble le modèle texte à 8 000 étapes et le décodeur
+A affiné, figé à **6 500 étapes de sa continuation GAN**. Elle utilise les poids
+`last` bruts, pas une sélection EMA. Le corpus de distillation comporte
+12 000 phrases françaises d'apprentissage, 500 de validation et 500 de test.
+
+**Limites :** une seule voix, français uniquement, quelques artefacts résiduels
+sur les consonnes, normalisation limitée aux formes courantes. La qualité et
+les prononciations du teacher restent des limites. Les autres langues et le
+clonage de voix ne sont pas pris en charge. v0 est une première release expérimentale.
+
+## Pour aller plus loin
+
+[Évaluation reproductible](https://github.com/IvannP39/Paradis-TTS-release/blob/main/evaluation/README.md) ·
+[Architecture et exports](https://github.com/IvannP39/Paradis-TTS-release/blob/main/docs/MODEL.md) ·
+[Normalisation française](https://github.com/IvannP39/Paradis-TTS-release/blob/main/docs/PHASE10_NORMALIZATION.md) ·
+[Code du runtime](https://github.com/IvannP39/Paradis-TTS-release/tree/main/paradis_tts) ·
+[Licences et attributions](https://github.com/IvannP39/Paradis-TTS-release/blob/main/docs/RELEASE_LICENSES.md)
+
+Code et poids : Apache-2.0. Textes Wikipédia : licences CC BY-SA séparées.
+Le G2P installé par pip comprend des composants GPL ; le runtime complet n'est
+pas présenté comme entièrement permissif. Voir les notices avant redistribution.

paradis_tts-0.1.1/README.md

@@ -0,0 +1,99 @@
+<p align="center"><img src="https://raw.githubusercontent.com/IvannP39/Paradis-TTS-release/main/assets/paradis-banner.png" alt="Paradis — Synthèse vocale française sur CPU" width="100%"></p>
+
+<p align="center">
+  <a href="https://github.com/IvannP39/Paradis-TTS-release/releases/tag/v0"><img alt="Release v0" src="https://img.shields.io/badge/release-v0-9ee8cb?style=flat-square"></a>
+  <a href="https://huggingface.co/IvannP/Paradis-TTS"><img alt="Hugging Face" src="https://img.shields.io/badge/Hugging_Face-mod%C3%A8les-ffd681?style=flat-square"></a>
+  <img alt="CPU et ONNX" src="https://img.shields.io/badge/runtime-CPU_%C2%B7_ONNX-c3dbe6?style=flat-square">
+  <a href="https://github.com/IvannP39/Paradis-TTS-release/blob/main/LICENSE"><img alt="Apache 2.0" src="https://img.shields.io/badge/code_%26_poids-Apache_2.0-c3dbe6?style=flat-square"></a>
+</p>
+
+**Une voix française compacte, directement dans votre application.**
+Paradis-TTS transforme du texte en audio sur CPU, avec 8,08 millions de paramètres,
+des poids ONNX FP32 ou INT8, et un post-traitement intégré. Après le premier
+téléchargement, la synthèse fonctionne entièrement hors ligne.
+
+[Écouter la voix](https://huggingface.co/IvannP/Paradis-TTS#écouter) ·
+[Télécharger v0](https://github.com/IvannP39/Paradis-TTS-release/releases/tag/v0) ·
+[Documentation Python](https://github.com/IvannP39/Paradis-TTS-release/blob/main/docs/PYTHON_PACKAGE.md)
+
+## Essayer
+
+Python 3.10–3.12. Installer le wheel public :
+
+```bash
+python -m pip install https://github.com/IvannP39/Paradis-TTS-release/releases/download/v0/paradis_tts-0.1.1-py3-none-any.whl
+```
+
+```python
+from paradis_tts import ParadisTTS
+
+tts = ParadisTTS()
+audio = tts("Bonjour tout le monde.")
+tts.save(audio, "bonjour.wav")
+```
+
+La construction de `ParadisTTS()` télécharge les poids FP32 depuis Hugging Face
+et les garde en cache après vérification SHA256. Aucun GPU, PyTorch ni
+Kokoro n'est nécessaire. `audio` est un tableau NumPy mono, `float32`, à 24 kHz.
+Le package est prêt pour PyPI ; l'installation ci-dessus utilise la release
+GitHub et ne suppose pas une publication dans l'index PyPI.
+
+## Choisir sa version
+
+| | FP32 | INT8 |
+|---|---:|---:|
+| Archive à télécharger | 30.21 Mo | 8.21 Mo |
+| Trois graphes ONNX | 32,82 Mo | 9,19 Mo |
+| Paramètres | 8 082 881 | 8 082 881 |
+| Poids | Flottants | Entiers 8 bits, déquantifiés au calcul |
+
+```python
+tts = ParadisTTS(variant="int8")
+tts = ParadisTTS(post_traitement=False)  # sortie brute
+tts = ParadisTTS(model_folder="chemin/vers/fp32")  # archive locale décompressée
+```
+
+Le profil audio par défaut associe le filtre de phase 97, une restauration de
+présence jusqu'à 2,5 dB et deux adoucissements du spectre à 1 et 1,5 dB.
+[Réglages et usage hors ligne](https://github.com/IvannP39/Paradis-TTS-release/blob/main/docs/PYTHON_PACKAGE.md).
+L'INT8 réduit le téléchargement ; il ne garantit pas une exécution plus rapide
+et peut modifier la voix. Le FP32 est le choix par défaut.
+
+## Mesures v0
+
+300 phrases inédites, articles séparés du corpus de distillation. CPU AMD Ryzen 7 5800H, Windows, deux threads configurés dans ONNX Runtime/PyTorch.
+
+| Moteur | WER ↓ | DNSMOS global ↑ | RTF médian ↓ | Pic RSS |
+|---|---:|---:|---:|---:|
+| Paradis FP32 | 12.51 % | 3.36 | 0.175 | 374 Mio |
+| Paradis INT8 | 12.70 % | 3.35 | 0.183 | 355 Mio |
+| Kokoro ff_siwis | 12.33 % | 3.42 | 0.719 | 4405 Mio |
+| Piper siwis medium | 16.47 % | 3.25 | 0.119 | 497 Mio |
+
+WER : taux d’erreurs de mots mesuré par Whisper Small en français. DNSMOS P.835 est un proxy parole/bruit, **pas une note d’écoute humaine ni une mesure suffisante de naturalité**. RTF < 1 signifie une génération plus rapide que la lecture. Les mesures ont eu lieu sur un portable partagé avec un entraînement GPU et d’autres tâches CPU ; elles ne constituent pas un classement en conditions isolées. [Protocole, scores par phrase et limites](https://github.com/IvannP39/Paradis-TTS-release/tree/main/evaluation).
+
+## D'où vient la voix ?
+
+Paradis adapte la méthode de [Paradee](https://github.com/sahilmahendrakar/paradee)
+au français et distille [Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M),
+voix `ff_siwis`. Cette v0 assemble le modèle texte à 8 000 étapes et le décodeur
+A affiné, figé à **6 500 étapes de sa continuation GAN**. Elle utilise les poids
+`last` bruts, pas une sélection EMA. Le corpus de distillation comporte
+12 000 phrases françaises d'apprentissage, 500 de validation et 500 de test.
+
+**Limites :** une seule voix, français uniquement, quelques artefacts résiduels
+sur les consonnes, normalisation limitée aux formes courantes. La qualité et
+les prononciations du teacher restent des limites. Les autres langues et le
+clonage de voix ne sont pas pris en charge. v0 est une première release expérimentale.
+
+## Pour aller plus loin
+
+[Évaluation reproductible](https://github.com/IvannP39/Paradis-TTS-release/blob/main/evaluation/README.md) ·
+[Architecture et exports](https://github.com/IvannP39/Paradis-TTS-release/blob/main/docs/MODEL.md) ·
+[Normalisation française](https://github.com/IvannP39/Paradis-TTS-release/blob/main/docs/PHASE10_NORMALIZATION.md) ·
+[Code du runtime](https://github.com/IvannP39/Paradis-TTS-release/tree/main/paradis_tts) ·
+[Licences et attributions](https://github.com/IvannP39/Paradis-TTS-release/blob/main/docs/RELEASE_LICENSES.md)
+
+Code et poids : Apache-2.0. Textes Wikipédia : licences CC BY-SA séparées.
+Le G2P installé par pip comprend des composants GPL ; le runtime complet n'est
+pas présenté comme entièrement permissif. Voir les notices avant redistribution.

paradis_tts-0.1.1/paradis_tts/__init__.py

@@ -0,0 +1,20 @@
+"""French student TTS with an offline phase 7 reference pipeline."""
+
+__all__ = ['ParadisTTS', 'OnnxTTS', 'PostProcessing', 'soften_audio', 'save_wav', 'postprocess_wav',
+           'download_model', '__version__']
+
+
+def __getattr__(name):
+    if name in ('ParadisTTS', '__version__', 'download_model'):
+        from paradis_tts import api
+        return getattr(api,name)
+    if name=='OnnxTTS':
+        from paradis_tts.onnx_runtime import OnnxTTS
+        return OnnxTTS
+    if name in ('PostProcessing','soften_audio','save_wav','postprocess_wav'):
+        from paradis_tts import audio
+        return getattr(audio,name)
+    if name=='SynthesisResult':
+        from paradis_tts.inference import ParadisTTS, SynthesisResult
+        return {'ParadisTTS': ParadisTTS, 'SynthesisResult': SynthesisResult}[name]
+    raise AttributeError(name)

paradis_tts-0.1.1/paradis_tts/__main__.py

@@ -0,0 +1,58 @@
+"""Offline ONNX speech/WAV CLI and standalone gentle postprocessing."""
+import argparse
+from dataclasses import replace
+import json
+from pathlib import Path
+from paradis_tts.audio import PostProcessing,read_wav,save_wav,soften_audio
+
+
+def main():
+    parser=argparse.ArgumentParser(prog='python -m paradis_tts')
+    commands=parser.add_subparsers(dest='command',required=True)
+    synth=commands.add_parser('synthesize',help='Generate an actual 24 kHz WAV using an ONNX bundle')
+    synth.add_argument('--model-folder','--bundle',dest='model_folder',type=Path)
+    synth.add_argument('--variant',choices=('fp32','int8'),default='fp32')
+    synth.add_argument('--no-post-traitement',action='store_true')
+    text=synth.add_mutually_exclusive_group(required=True)
+    text.add_argument('--text');text.add_argument('--text-file',type=Path)
+    synth.add_argument('--speed',type=float,default=1.)
+    synth.add_argument('--seed',type=int,default=1729)
+    synth.add_argument('--threads',type=int,default=2)
+    post=commands.add_parser('postprocess',help='Soften an existing mono 24 kHz PCM16 WAV')
+    post.add_argument('input',type=Path)
+    for command in (synth,post):
+        command.add_argument('--output',type=Path,required=True)
+        command.add_argument('--settings',type=Path,help='Standard settings or browser slider JSON')
+        command.add_argument('--overwrite',action='store_true')
+        for option in ('dynamic-db','upper-db','attack-db','syllable-db','smoothing'):
+            command.add_argument('--'+option,type=float)
+    args=parser.parse_args()
+    settings=PostProcessing.from_file(args.settings) if args.settings else None
+    aliases={'dynamic_db':'dynamic_soften_db','upper_db':'upper_soften_db',
+             'attack_db':'attack_soften_db','syllable_db':'syllable_soften_db','smoothing':'dynamics_smoothing'}
+    overrides={target:getattr(args,source) for source,target in aliases.items() if getattr(args,source) is not None}
+    if args.command=='synthesize' and args.no_post_traitement and (settings is not None or overrides):
+        parser.error('--no-post-traitement cannot be combined with processing settings')
+    if args.command=='synthesize':
+        from paradis_tts.api import ParadisTTS
+        model=ParadisTTS(model_folder=args.model_folder,threads=args.threads,postprocessing=settings,
+                         variant=args.variant,post_traitement=not args.no_post_traitement)
+        model.postprocessing=replace(model.postprocessing,**overrides)
+        text=args.text if args.text is not None else args.text_file.read_text(encoding='utf-8-sig')
+        result=model.to_file(text,args.output,seed=args.seed,speed=args.speed,overwrite=args.overwrite)
+        print(json.dumps({'output':str(args.output),'normalized_text':result.normalized_text,**result.audit()},ensure_ascii=False))
+    else:
+        settings=replace(settings or PostProcessing(),**overrides)
+        signal=read_wav(args.input)
+        audio=soften_audio(signal,dynamic_db=settings.dynamic_soften_db,upper_db=settings.upper_soften_db,
+            attack_db=settings.attack_soften_db,syllable_db=settings.syllable_soften_db,
+            smoothing=settings.dynamics_smoothing,match_level=settings.softening_match_level)
+        save_wav(audio,args.output,overwrite=args.overwrite)
+        metadata={'input':str(args.input),'stage':'softening_only','phase_filter_applied':False,
+            'settings':replace(settings,phase_lock_frames=0,presence_restore=False).to_dict(),
+            'samples':len(audio),'sample_rate':24000}
+        args.output.with_suffix(args.output.suffix+'.json').write_text(json.dumps(metadata,indent=2)+'\n',encoding='utf-8')
+        print(json.dumps({'output':str(args.output),'sample_rate':24000,'samples':len(audio)}))
+
+
+if __name__=='__main__': main()