Release v1.10.6

What's Changed

• Resolve issues with using pre-installed onnxruntime by @hantengc in #1058
• Fix possible segfault in C API. by @csukuangfj in #1059
• Fix CI tests by @csukuangfj in #1061
• Support .Net framework 2.0 by @csukuangfj in #1062
• Support silero_vad version 5 by @csukuangfj in #1064

Full Changelog: v1.10.2...v1.10.6

Release v1.10.2

What's Changed

• Flutter demo for real-time speech recognition by @csukuangfj in #1042
• Update READEM to include links to pre-built Flutter APPs by @csukuangfj in #1043
• Add VAD + microphone example for Java API. by @csukuangfj in #1045
• Add VAD + Non-streaming ASR + microphone examples for Java API by @csukuangfj in #1046
• Add streaming ASR example from a microphone for Java API by @csukuangfj in #1047
• Fix the alsa-lib version to v1.2.12 by @csukuangfj in #1048
• 修改示例项目结构 by @dfengpo in #1049
• Remove unused files from .Net examples by @csukuangfj in #1051
• Add non-streaming zipformer Android APK for Korean by @csukuangfj in #1052
• fix a bug for wenet streaming model. by @csukuangfj in #1054
• Fix passing C# string to C++ by @csukuangfj in #1055
• Publish pre-built jni libs for windows and osx by @csukuangfj in #1056

Full Changelog: v1.10.1...v1.10.2

v1.10.1

What's Changed

• Publish pre-compiled libs for jni (linux x64) by @csukuangfj in #1026
• Swift API for keyword spotting. by @csukuangfj in #1027
• fix generate-subtitles.py bug by @xiaokuang95 in #1029
• Add Python API support for Offline LM rescoring by @SilverSulfide in #1033
• Support clang-tidy by @csukuangfj in #1034
• offline transducer: treat unk as blank by @Chung-I in #1005
• Build Android APK for Thai by @csukuangfj in #1036
• fix typo by @pengzhendong in #1038
• Enable to stop TTS generation by @csukuangfj in #1041

New Contributors

• @xiaokuang95 made their first contribution in #1029
• @SilverSulfide made their first contribution in #1033
• @Chung-I made their first contribution in #1005

Full Changelog: v1.10.0...v1.10.1

Release v1.10.0

What's Changed

• Use CI to publish dart packages by @csukuangfj in #1001
• Publish osx-arm64 nuget package for .Net by @csukuangfj in #1003
• Update README by @csukuangfj in #1004
• scale value fix by @lovemefan in #1006
• Add non-streaming ASR examples for Dart API by @csukuangfj in #1007
• Add streaming ASR examples for Dart API by @csukuangfj in #1009
• Add TTS API and examples for Dart by @csukuangfj in #1010
• Add example description for the dart package by @csukuangfj in #1011
• Add Android APK for Korean by @csukuangfj in #1015
• Release v1.9.30 by @csukuangfj in #1016
• Add inverse text normalization for non-streaming ASR by @csukuangfj in #1017
• Inverse text normalization API for other programming languages by @csukuangfj in #1019
• Add inverse text normalization for online ASR by @csukuangfj in #1020
• Inverse text normalization API of streaming ASR for various programming languages by @csukuangfj in #1022

Full Changelog: v1.9.29...v1.10.0

Release v1.9.29

What's Changed

• Update features.h by @eltociear in #994
• fix kws for WebAssembly by @csukuangfj in #999
• Add VAD example for Dart API by @csukuangfj in #996

New Contributors

• @eltociear made their first contribution in #994

Full Changelog: v1.9.28...v1.9.29

Release v1.9.28

What's Changed

• Fix punctuation by @csukuangfj in #976
• initial tensorrt ep commit by @manickavela29 in #921
• Support getting word IDs for CTC HLG decoding. by @csukuangfj in #978
• Add Python example to show how to register speakers dynamically for speaker ID. by @csukuangfj in #986
• add more text-to-speech models from piper by @csukuangfj in #988
• store speed in SharedPreferences by @gilcu3 in #991
• Limit the maximum segment length for VAD. by @csukuangfj in #990
• Fix CI errors. by @csukuangfj in #993

New Contributors

• @gilcu3 made their first contribution in #991

Full Changelog: v1.9.27...v1.9.28

Release v1.9.27

What's Changed

• Update test-dot-net.yaml by @dfengpo in #960
• Wrap offline ASR APIs to dart by @csukuangfj in #961
• Update c-api.h to hotwords by @9728Lin in #962
• Add a VAD Python example to remove silences from a file. by @csukuangfj in #963
• export telespeech ctc models to sherpa-onnx by @csukuangfj in #968
• Fix CI by @csukuangfj in #964
• Add C++ runtime for Tele-AI/TeleSpeech-ASR by @csukuangfj in #970

New Contributors

• @9728Lin made their first contribution in #962

Full Changelog: v1.9.26...v1.9.27

Release v1.9.26

What's Changed

• Encode hotwords in C++ side by @pkufool in #828
• Fix Go tests by @csukuangfj in #897
• Fix CI tests. by @csukuangfj in #898
• Add Flutter example for speaker identification by @csukuangfj in #894
• Add recording permission for iOS App. by @csukuangfj in #900
• Fix CI for JavaScript and Python APIs. by @csukuangfj in #901
• Fix reading wave files generated by NAudio. by @csukuangfj in #903
• Add Dart API for VAD by @csukuangfj in #904
• Fix CI tests. by @csukuangfj in #907
• fix detecting node-addon packages by @csukuangfj in #908
• Support reading waves from NAudio. by @csukuangfj in #914
• Support Windows arm64 by @csukuangfj in #911
• fix building errors introduced by simple-sentencepiece by @csukuangfj in #915
• Update offline-ctc-greedy-search-decoder.cc by @Dadoou in #917
• Add Flutter GUI example for VAD with a microphone. by @csukuangfj in #905
• 提供设置关键词的api，方便动态调整关键词来进行识别 by @hantengc in #923
• add a new tts piper model by @csukuangfj in #927
• Support not using external buffers for node-addon by @csukuangfj in #925
• Add VAD demo for Java API by @csukuangfj in #928
• Add KWS examples for Java API by @csukuangfj in #930
• Reset encoder states on endpointing for streaming transducer. by @csukuangfj in #924
• fix node-addaon-api for vad by @csukuangfj in #932
• update c-api.h by @RuleNumber1 in #937
• Added tokens, tokens_arr and json for offline recognizer result by @leohuang2013 in #936
• fix: Typo 'maxNumSenetences' in SherpaOnnx.swift by @BrutalCoding in #939
• Split online.cs and offline.csFile by @dfengpo in #941
• Add Dart API for streaming ASR by @csukuangfj in #933
• Add C++ runtime for streaming faster conformer transducer from NeMo. by @sangeet2020 in #889
• Fix nemo streaming transducer greedy search by @csukuangfj in #944
• Wrap punctuation APIs to C#. by @csukuangfj in #945
• Wrap VAD APIs to C# by @csukuangfj in #946
• release v1.9.26 by @csukuangfj in #947
• Fix building for Android by @csukuangfj in #949
• Support customize scores for hotwords by @pkufool in #926
• Add address sanitizer and undefined behavior sanitizer by @csukuangfj in #951

New Contributors

• @Dadoou made their first contribution in #917
• @RuleNumber1 made their first contribution in #937
• @BrutalCoding made their first contribution in #939
• @dfengpo made their first contribution in #941
• @sangeet2020 made their first contribution in #889

Full Changelog: v1.9.25...v1.9.26

Release v1.9.25

What's Changed

• Add node-addon-api for VAD by @csukuangfj in #864
• Fix node addon tests by @csukuangfj in #865
• Add Android APKs for NeMo CTC models. by @csukuangfj in #866
• Add streaming CTC ASR APIs for node-addon-api by @csukuangfj in #867
• Add non-streaming ASR APIs for node-addon-api by @csukuangfj in #868
• Compiler Error and Minor Bug fix by @manickavela29 in #870
• Add TTS for node-addon-api by @csukuangfj in #871
• Add spoken language identification for node-addon-api by @csukuangfj in #872
• Refactor node-addon-api to remove duplicate. by @csukuangfj in #873
• Add speaker identification APIs for node-addon-api by @csukuangfj in #874
• Add audio tagging APIs for node-addon-api by @csukuangfj in #875
• Support adding puncutations to text for node-addon-api by @csukuangfj in #876
• Add keyword spotting API for node-addon-api by @csukuangfj in #877
• Fix sherpa-onnx-node-version in node examples by @csukuangfj in #879
• Update CMakeLists.txt by @linziguan in #881
• Fix Java API examples by @csukuangfj in #883
• Fix a typo in jni by @csukuangfj in #885
• Add tail_paddings to Whisper C API. by @csukuangfj in #886

New Contributors

• @linziguan made their first contribution in #881

Full Changelog: v1.9.24...v1.9.25

Release v1.9.24

What's Changed

• Add CTC HLG decoding for JNI by @csukuangfj in #810
• Add function 'tolowerUnicode' in sherpa-onnx-microphone (fix #791) by @daniel-dona in #812
• Add Java API for text-to-speech by @csukuangfj in #811
• Adding temperature scaling on Joiner logits: by @KarelVesely84 in #789
• Fix building wheels for macOS by @csukuangfj in #814
• Fix C# to support Chinese tts models using jieba by @csukuangfj in #815
• Fix a bug for offline paraformer by @csukuangfj in #816
• Add Java API for spoken language identification with whisper multilingual models by @csukuangfj in #817
• Add Java and Kotlin API for punctuation models by @csukuangfj in #818
• Add Java API for audio tagging by @csukuangfj in #820
• Add Java API for speaker identification by @csukuangfj in #822
• Fix typos in JNI TTS by @csukuangfj in #824
• Begin to add node-addon-api for sherpa-onnx by @csukuangfj in #826
• Publish node-addon-api wrapper for sherpa-onnx as npm packages by @csukuangfj in #829
• Update 3dspeaker/export-onnx.py by @chiiyeh in #836
• Upload two more 3d-speaker models by @csukuangfj in #837
• Publish npm package with node-addon-api for Windows by @csukuangfj in #838
• Add links to pre-built APKs and pre-trained models to README. by @csukuangfj in #840
• Publish node-addon-api npm package for linux arm64 by @csukuangfj in #841
• Export NeMo FastConformer Hybrid Transducer-CTC Large Streaming to ONNX. by @csukuangfj in #843
• Export NeMo FastConformer Hybrid Transducer Large Streaming to ONNX by @csukuangfj in #844
• Export non-streaming NeMo faster conformer hybrid transducer and ctc to sherpa-onnx by @csukuangfj in #847
• Add C++ support for non-streaming NeMo fast conformer hybrid transducer ctc (the ctc branch) by @csukuangfj in #848
• Add C++ runtime for non-streaming faster conformer transducer from NeMo. by @csukuangfj in #854
• Solve the issue of missing the last sentence with punctuation by @yh646492956 in #856
• Add C++ support for streaming NeMo CTC models. by @csukuangfj in #857
• Add more streaming ASR methods for node-addon-api by @csukuangfj in #860
• Fix Python TTS examples for models using jieba. by @csukuangfj in #861
• Add Speaker ID demo for C# by @csukuangfj in #862

New Contributors

• @daniel-dona made their first contribution in #812
• @yh646492956 made their first contribution in #856

Full Changelog: v1.9.23...v1.9.24