v1.13.5

k2-fsa/sherpa-onnxv1.13.5Aug 11, 2026by github-actions[bot]

AI Summary

A major feature release introducing support for Swift Package Manager (SPM), Flutter/Dart Web, CUDA 13, and Inflect TTS, alongside extensive QNN support for Nemotron and Moonshine models, Java API improvements, and various bug fixes.

Key Highlights

  • Swift Package Manager (SPM) support
  • Flutter/Dart Web support via WebAssembly
  • CUDA 13 support
  • Inflect TTS support
  • QNN support for Nemotron and Moonshine models

New Features

  • SPM support
  • Flutter/Dart Web support
  • CUDA 13 support
  • Inflect TTS support
  • QNN support for Nemotron and Moonshine models
  • Java API Maven/Gradle examples

Full Release Notes

## What's Changed
* Re-export nemotron-3.5-asr-streaming-0.6b to ONNX by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3732
* Fix building Android KWS demo by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3733
* Refactor ONNX export script for nemotron-3.5-asr-streaming-0.6b by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3734
* Build a docker image to setup the QNN SDK environment by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3736
* Export nemotron-3.5-asr-streaming-0.6b to QNN by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3741
* Add Android shared-linking support to sherpa-onnx-sys by @willwade in https://github.com/k2-fsa/sherpa-onnx/pull/3739
* Fix build warnings by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3742
* Fix ScaleSilence copying past the pause interval when scale > 1 by @ekenberg in https://github.com/k2-fsa/sherpa-onnx/pull/3744
* Guard ScaleSilence against invalid silence scales by @ekenberg in https://github.com/k2-fsa/sherpa-onnx/pull/3745
* Align the silence scale range between Validate() and ScaleSilence by @ekenberg in https://github.com/k2-fsa/sherpa-onnx/pull/3747
* Export Moonshine ASR models to QNN by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3756
* Add C++ runtime for Moonshine ASR with QNN for Qualcomm NPU by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3758
* Upload vits-piper-pt_BR-cadu-medium to huggingface by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3763
* Fix uploading Piper TTS models by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3774
* Fix process abort when espeak-ng rejects the voice (e.g. invalid --kokoro-lang) by @ekenberg in https://github.com/k2-fsa/sherpa-onnx/pull/3749
* Fix dropped diacritics in Supertonic TTS text frontend by @bogdanr in https://github.com/k2-fsa/sherpa-onnx/pull/3750
* Add Fono to 'Projects using sherpa-onnx' by @bogdanr in https://github.com/k2-fsa/sherpa-onnx/pull/3775
* Allocate FireRedASR decoder KV cache by estimated need instead of max… by @Kn0688 in https://github.com/k2-fsa/sherpa-onnx/pull/3777
* Add maven examples for Java API by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3783
* Add Java API examples with gradle by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3784
* Fix greedy search decoding for Nemo streaming transducer by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3785
* Refactor building and testing Java API by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3786
* Fix adaptive KV cache for models with hard-coded cache length by @Kn0688 in https://github.com/k2-fsa/sherpa-onnx/pull/3787
* Add ten-vad Rust API example to remove silences from a file by @sportiz91 in https://github.com/k2-fsa/sherpa-onnx/pull/3778
* docs(rust): add FunASR Nano offline ASR example (#3210) by @stantheman0128 in https://github.com/k2-fsa/sherpa-onnx/pull/3772
* Fix use-after-free in async TTS progress callbacks by @kecoco16 in https://github.com/k2-fsa/sherpa-onnx/pull/3781
* Make the Pyannote segmentation window shift configurable by @JulianPscheid in https://github.com/k2-fsa/sherpa-onnx/pull/3769
* Print per-stage timing for offline speaker diarization in debug mode by @JulianPscheid in https://github.com/k2-fsa/sherpa-onnx/pull/3768
* Add Domia to the projects using sherpa-onnx by @kecoco16 in https://github.com/k2-fsa/sherpa-onnx/pull/3793
* Forward `SessionConfig.`-prefixed provider-config keys to Ort::SessionOptions::AddConfigEntry by @kecoco16 in https://github.com/k2-fsa/sherpa-onnx/pull/3792
* Fix macOS release code signatures by @LauraGPT in https://github.com/k2-fsa/sherpa-onnx/pull/3794
* Raise FireRedASR decode cap from 6 to 8 tokens/sec for fast speech by @Kn0688 in https://github.com/k2-fsa/sherpa-onnx/pull/3796
* Set FireRedASR default max_token_per_second to 8 by @Kn0688 in https://github.com/k2-fsa/sherpa-onnx/pull/3799
* Simplify build.gradle.kts for java api examples. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3788
* Test Java API on Windows arm64 by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3801
* fix UB by @x6prl in https://github.com/k2-fsa/sherpa-onnx/pull/3806
* fix(tts): insert pad after BOS in PiperPhonemesToIdsVits (#3721) by @stantheman0128 in https://github.com/k2-fsa/sherpa-onnx/pull/3770
* Export Inflect TTS models to sherpa-onnx by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3808
* Add API to get onnxruntime version. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3810
* Add Android demo for Inflect TTS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3811
* Build Python wheels for Windows arm64 by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3812
* build(cmake): update spacemit-ort version by @xiaotong-spacemit in https://github.com/k2-fsa/sherpa-onnx/pull/3814
* Support swift package manager (SPM) by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3816
* Publish an android-x64 .NET runtime package by @kfrancis in https://github.com/k2-fsa/sherpa-onnx/pull/3818
* Fix non_streaming_server.py crash with --decoding-method modified_beam_search by @slipstr34m in https://github.com/k2-fsa/sherpa-onnx/pull/3819
* Fix process crash when --kokoro-voices is missing or empty (#3748) by @slipstr34m in https://github.com/k2-fsa/sherpa-onnx/pull/3820
* Fix streaming paraformer feature frontend drift from its training config by @slipstr34m in https://github.com/k2-fsa/sherpa-onnx/pull/3821
* Use SPM in iOS examples by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3822
* Fix iOS examples using swift package manager by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3823
* Add Paraformer Rust API example add rust paraformer example by @nati2405 in https://github.com/k2-fsa/sherpa-onnx/pull/3707
* Add missing files for swift package manager by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3828
* Set onnxruntime version to 1.27.1 in SPM by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3830
* Refactor building xcframework for macOS and iOS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3831
* Support linking onnxruntime statically in xcframework with shared lib. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3833
* Support using SPM for Flutter on macOS and iOS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3835
* Fix building Python wheels on macOS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3837
* Disable pthread support in WebAssembly.  by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3836
* Fix Dart speaker diarization input buffer leak by @zhangheng2022 in https://github.com/k2-fsa/sherpa-onnx/pull/3838
* Fix offline Paraformer LFR boundary padding by @LauraGPT in https://github.com/k2-fsa/sherpa-onnx/pull/3839
* docs: add qwen-audio-agent to projects using sherpa-onnx by @x-lixu in https://github.com/k2-fsa/sherpa-onnx/pull/3841
* Add Flutter/Dart Web support via WebAssembly by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3842
* Build libs and Python wheels for CUDA 13 by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3844
* Add punctuation examples for Flutter by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3846
* Add Persian NeMo CTC ASR models (shenava koochik/rizeh/rizeh-pizeh) by @mah92 in https://github.com/k2-fsa/sherpa-onnx/pull/3825
* Add CI for Flutter punctuation examples by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3847
* Add emotion_id input to offline VITS TTS by @matiaslin in https://github.com/k2-fsa/sherpa-onnx/pull/3849
* Add support for latest DPDFNet models and offline attenuation limit by @danielr-ceva in https://github.com/k2-fsa/sherpa-onnx/pull/3824
* kotlin-api: validate native ptr after creation by @sigkillsdottir in https://github.com/k2-fsa/sherpa-onnx/pull/3851
* Use onnxruntime 1.27.1 for Linux aarch64 and Android by @yentur in https://github.com/k2-fsa/sherpa-onnx/pull/3850
* fix(asr): stop forcing lowercase in mic and ALSA display (#3621) by @stantheman0128 in https://github.com/k2-fsa/sherpa-onnx/pull/3771
* Add Flutter examples for VAD by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3856
* Fix Kotlin Syntax errors by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3860
* Update onnxruntime to v1.27.1 by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3861
* Fix float32 catastrophic cancellation in NemoNormalizePerFeature by @Eoin-Houstoun in https://github.com/k2-fsa/sherpa-onnx/pull/3857
* Fix float32 catastrophic cancellation in variance computation by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3862
* Release v1.13.5 by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/3863

## New Contributors
* @willwade made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3739
* @ekenberg made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3744
* @bogdanr made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3750
* @Kn0688 made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3777
* @sportiz91 made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3778
* @stantheman0128 made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3772
* @kecoco16 made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3781
* @LauraGPT made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3794
* @x6prl made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3806
* @xiaotong-spacemit made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3814
* @kfrancis made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3818
* @slipstr34m made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3819
* @nati2405 made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3707
* @zhangheng2022 made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3838
* @x-lixu made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3841
* @sigkillsdottir made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3851
* @yentur made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3850
* @Eoin-Houstoun made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/3857

**Full Changelog**: https://github.com/k2-fsa/sherpa-onnx/compare/v1.13.4...v1.13.5