xuning / sherpaonnx

Co-authored-by: Aruxxxi <xiangcl@zhisuan.com>

This PR implements support for specifying pronunciations of phrases in Chinese TTS by modifying the lexicon processing logic. The change introduces a greedy longest-match algorithm that attempts to match multi-word phrases before falling back to individual word processing.

This PR adds support for exporting two new whisper distil models (distil-large-v3 and distil-large-v3.5) to ONNX format for use with sherpa-onnx. The changes enable these models to be processed through the existing export pipeline.

- Added support for distil-large-v3 and distil-large-v3.5 models in the export script
- Updated GitHub workflow to include the new models in the CI matrix
- Configured proper n_mels parameter (128) for the new distil models

This PR updates version information across all Android applications in the sherpa-onnx project to version 1.12.9 with version code 20250817. The changes automate version updates through a release script and apply consistent versioning across all Android app modules.

This PR refactors CI test configurations by removing pull request triggers from multiple GitHub Actions workflows and fixes a bug in the cosine similarity calculation. Additionally, it updates Python version paths for newer 3.13.6 release.

This PR adds support for new streaming ASR models from VOSK (Russian) and Kroko (German) to the sherpa-onnx project. It integrates three new models: one German Kroko streaming model and two Russian VOSK streaming models (regular and int8 quantized versions).

- Adds configuration for three new streaming ASR models (indices 24-26)
- Updates APK generation scripts to include the new models
- Modifies GitHub workflow for model upload and deployment

This PR adds support for the newer version (v3) of NVIDIA's parakeet-tdt-0.6b model by exporting it to sherpa-onnx format. The v3 model supports 25 languages, maintaining the same usage pattern as v2 but with improved language coverage.

Co-authored-by: wangmh <minghu.wang@shenyiai.net>

This PR improves Android APK build process by specifying target ABIs during gradle assembly and fixing arithmetic precision issues in decoder calculations. The changes ensure that APKs are built for specific architectures rather than all architectures at once, and correct integer division operations that could lead to precision loss.

- Adds ABI-specific gradle build parameters to target specific architectures during APK assembly
- Updates APK output paths from outputs/apk to intermediates/apk to match gradle's ABI-filtered build structure
- Fixes integer division precision issues in decoder calculations by using floating-point division