Eureka Ilwa Embedded Voice 1.0.0

Engine: sherpa-onnx 1.13.8 (Apache-2.0), https://github.com/k2-fsa/sherpa-onnx/tree/v1.13.8
Native release artifacts include ONNX Runtime (MIT) and eSpeak NG (GPL-3.0-or-later).
Corresponding upstream source/build recipes:
https://github.com/k2-fsa/sherpa-onnx/tree/v1.13.8/cmake
https://github.com/espeak-ng/espeak-ng
https://github.com/microsoft/onnxruntime
The bundled native library, its build and transitive components retain their respective licenses.
License texts and notices accompany this package; distribution must retain them.

Voice: es_ES-sharvard-medium, Spanish (Spain), sample rate 22050 Hz.
Speaker IDs in official configuration: M=0, F=1. Ilwa selects F=1.
Model adapted for sherpa-onnx from Piper; exact artifact and SHA-256 in dependencies.lock.json.
Original model repository: https://huggingface.co/rhasspy/piper-voices/tree/main/es/es_ES/sharvard/medium
Dataset: Sharvard, University of Edinburgh, https://datashare.ed.ac.uk/handle/10283/574
Dataset license: Creative Commons Attribution 3.0 (CC BY 3.0).
Model card is included verbatim; attribution is retained here and in MODEL_CARD.txt.

No Python interpreter, HTTP service or user speech/text is included in this package.
Editable integration source: META-INF/ilwa-voice/src/EmbeddedVoice.java.
The reproducible package recipe is tools/ilwa-voice-java/build.ps1 in the Eureka source tree.