Release v1.12.18 · k2-fsa/sherpa-onnx

What's Changed

Fix CI by @csukuangfj in #2786
export omniASR_CTC_1B from https://github.com/facebookresearch/omnilingual-asr by @csukuangfj in #2788
Add C++ QNN support for SenseVoice by @csukuangfj in #2793
Export models for CANN toolkit 7.0 by @csukuangfj in #2795
Support hotwords with byte level bpe by @csukuangfj in #2802
Add Android demo with QNN (Qualcomm NPU) for SenseVoice ASR by @csukuangfj in #2803
Export zipformer ctc models to QNN by @csukuangfj in #2815
Add spaces between English words for Homophone replacer. by @csukuangfj in #2817
Add C++ QNN support for Zipformer CTC models. by @csukuangfj in #2809
Limit symbol visibility in the shared libraries by @csukuangfj in #2822
Fix warnings for initializing tts lexicon. by @csukuangfj in #2823
Export zipformer ctc models to Ascend NPU by @csukuangfj in #2824
Refactor scripts for exporting models to Ascend NPU. by @csukuangfj in #2825
Add C++ support for Zipformer CTC on Ascend NPU by @csukuangfj in #2826
Fix segfault when non-wav file is passed to ReadWave by @jcheng5 in #2821
Avoid calling rknn_dup_context(). by @csukuangfj in #2828
Add C++ support for Paraformer with RK NPU by @csukuangfj in #2829
Update README to include NPU support by @csukuangfj in #2830
Support running whisper large v3 with external data weight by @csukuangfj in #2807
Release v1.12.18 by @csukuangfj in #2831

Full Changelog: v1.12.17...v1.12.18