What's Changed

• Fix kws ci by @pkufool in https://github.com/k2-fsa/sherpa-onnx/pull/540
• Fix cmake variables to point to the project root directory. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/545
• add blank_penalty for offline transducer by @chiiyeh in https://github.com/k2-fsa/sherpa-onnx/pull/542
• add hotwords docstring to offline_recognizer and online_recognizer by @chiiyeh in https://github.com/k2-fsa/sherpa-onnx/pull/546
• add blank_penalty for online transducer by @chiiyeh in https://github.com/k2-fsa/sherpa-onnx/pull/548
• Fixes issue #535 , fix hexa 1-char tokens in ASR output. by @vesis84 in https://github.com/k2-fsa/sherpa-onnx/pull/550
• Ensure input for speaker ID is a valid number. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/552
• Run TTS engine service without starting the app. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/553

New Contributors

• @chiiyeh made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/542
• @vesis84 made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/550

Full Changelog: https://github.com/k2-fsa/sherpa-onnx/compare/v1.9.8...v1.9.9

What's Changed

• Add missing field for two-pass APK. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/511
• Fix Byte BPE string results for Python. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/512
• Fix #510 by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/513
• Use high_freq -400 in computing fbank features. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/515
• Use NDK 22.1 for android build by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/518
• Add runtime support for wespeaker models by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/516
• Support exporting models to onnx from 3D-Speaker by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/522
• Fix publishing nuget packages. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/525
• Add C++ runtime for models from 3d-speaker by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/523
• Export speaker verification models from NeMo to ONNX by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/526
• Add C++ runtime for speaker verification models from NeMo by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/527
• Android TTS APKs for Persian by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/529
• Fix setting speaker ID for Android TTS Engine. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/530
• Add a Persian and a Slovenian model from Piper for Android TTS. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/531
• Add Python API examples for speaker recognition with VAD and ASR. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/532
• Refactor the UI of Android TTS engine by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/533
• decoder for open vocabulary keyword spotting by @pkufool in https://github.com/k2-fsa/sherpa-onnx/pull/505
• Change model url from modelscope to github by @pkufool in https://github.com/k2-fsa/sherpa-onnx/pull/538
• Add Android demo for speaker recognition by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/536

Full Changelog: https://github.com/k2-fsa/sherpa-onnx/compare/v1.9.7...v1.9.8

• Decoder for open vocabulary keyword spotting by @pkufool https://github.com/k2-fsa/sherpa-onnx/pull/505

This page contains models for keyword spotting.

What's Changed

• Replace Android system TTS engine by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/508
• Build text-to-speech engine APKs by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/509

Full Changelog: https://github.com/k2-fsa/sherpa-onnx/compare/v1.9.5...v1.9.7

What's Changed

• Fix building wheels for Linux. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/484
• Fix CI by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/485
• Print informative error messages for sherpa-onnx-alsa on errors. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/486
• Keep multiple threads from calling into espeak-ng at the same time by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/489
• Fix whisper test script for the latest onnxruntime. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/494
• Release Python GIL in C++ class constructor by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/493
• Support streaming zipformer CTC by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/496

Full Changelog: https://github.com/k2-fsa/sherpa-onnx/compare/v1.9.4...v1.9.5

What's Changed

• Give an informative log for whisper on exceptions. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/473
• convert wespeaker models to sherpa-onnx by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/475
• Fix releasing go packages by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/476
• Support playing as it is generating for Android by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/477
• Fix android tts audio buffer size and fix CI. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/478
• Add two GLaDOS TTS models by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/481
• Play generated audio using alsa for TTS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/482

Full Changelog: https://github.com/k2-fsa/sherpa-onnx/compare/v1.9.1...v1.9.4

This release contains speaker recognition models for sherpa-onnx.

What's Changed

• Remove the 30-second constraint from whisper. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/471
• Support distil-small.en whisper by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/472

Full Changelog: https://github.com/k2-fsa/sherpa-onnx/compare/v1.9.0...v1.9.1

What's Changed

• Build building for iOS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/430
• Judge before UseCachedDecoderOut by @HieDean in https://github.com/k2-fsa/sherpa-onnx/pull/431
• Build MFC examples for Windows x86 (Win32) by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/434
• Replace Clone() with View() by @HieDean in https://github.com/k2-fsa/sherpa-onnx/pull/432
• Refactor CI scripts about building wheels by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/436
• support nodejs by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/438
• Add Swift API for TTS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/439
• Text-to-speech for iOS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/443
• Lock before push_back the deque for thread safety by @HieDean in https://github.com/k2-fsa/sherpa-onnx/pull/445
• Update to onnxruntime 1.16.3 by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/446
• Fix reading tokens.txt on Windows by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/448
• Fix nodejs on Windows by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/450
• Release GIL to support multithreading in Python websocket servers. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/451
• Support piper-phonemize by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/452
• Use piper-phonemize to convert text to token IDs by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/453
• Fix CI by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/456
• Play generated audio as it is generating. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/457
• Break text into sentences for tts. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/460
• Support playing generated audio as it is generating for MFC. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/462
• Fix building for .Net by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/463
• Use espeak-ng for coqui-ai/TTS VITS English models. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/466
• Support Ukrainian VITS models from coqui-ai/TTS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/469
• Release v1.9.0 by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/470

New Contributors

• @HieDean made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/431

Full Changelog: https://github.com/k2-fsa/sherpa-onnx/compare/v1.8.10...v1.9.0

This release contains pre-trained ASR models.

Please refer to
https://k2-fsa.github.io/sherpa/onnx/pretrained_models/index.html
for more models.

This release contains pre-trained tts models.

Please refer to
https://k2-fsa.github.io/sherpa/onnx/tts/pretrained_models/index.html
for more models.

What's Changed

• Fix punctuations in tts for Chinese by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/417
• Build Android APKs for VITS models from Coqui-ai/TTS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/419
• Add a C++ example to show streaming VAD + non-streaming ASR. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/420
• Update onnxruntime from v1.16.1 to v1.16.2 by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/421
• Resize circular buffer on overflow by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/422
• Add scripts to export ASR models from wenet to ONNX by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/425
• Support non-streaming WeNet CTC models. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/426
• Support streaming conformer CTC models from wenet by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/427
• Add Python APIs for WeNet CTC models by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/428

Full Changelog: https://github.com/k2-fsa/sherpa-onnx/compare/v1.8.9...v1.8.10

TTS APKs

Please see
https://k2-fsa.github.io/sherpa/onnx/tts/apk.html

What's Changed

• Support VITS TTS models from coqui-ai/TTS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/416

Full Changelog: https://github.com/k2-fsa/sherpa-onnx/compare/v1.8.8...v1.8.9

What's Changed

• Add C# TTS API by @LKZMuZiLi in https://github.com/k2-fsa/sherpa-onnx/pull/399
• Upload TTS APKs to huggingface by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/400
• Support static linking onnxruntime lib for 32-bit arm by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/401
• Support static linking onnxruntime for 64-bit ARM by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/402
• Support linking onnxruntime statically for macOS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/403
• Use a single static lib file for onnxruntime on Windows by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/404
• Update to onnxruntime v1.16.1 by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/406
• Support text normalization via rule FST by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/407
• Catch exception from whisper by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/408
• Support Chinese polyphones in TTS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/409
• support reading rule FST for Android TTS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/410
• Support distil-whisper by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/411
• add --tts-rule-fsts argument at offline-tts.py by @longshiming in https://github.com/k2-fsa/sherpa-onnx/pull/413
• Release v1.8.8 by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/414

New Contributors

• @LKZMuZiLi made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/399

Full Changelog: https://github.com/k2-fsa/sherpa-onnx/compare/v1.8.7...v1.8.8

What's Changed

• Support German TTS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/394
• Support German umlauts in splitting UTF8 strings. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/395
• Support Spanish in TTS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/396
• Support French in TTS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/397

Full Changelog: https://github.com/k2-fsa/sherpa-onnx/compare/v1.8.6...v1.8.7

What's Changed

• Fix utf8 spliting for English by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/386
• include cstdint (debian, gcc-13.2) by @rouseabout in https://github.com/k2-fsa/sherpa-onnx/pull/388
• Fix splitting words containing ', e.g., I've by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/389
• Support vits models from piper by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/390
• Release v1.8.6 by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/391

New Contributors

• @rouseabout made their first contribution in https://github.com/k2-fsa/sherpa-onnx/pull/388

Full Changelog: https://github.com/k2-fsa/sherpa-onnx/compare/v1.8.5...v1.8.6

What's Changed

• Add MFC TTS example on Windows by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/378
• support specifying output filename in MFC tts example by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/380
• Add jni interface and kotlin API examples for TTS. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/381
• Fix jni test by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/382
• Add Android TTS demo by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/383
• support specifying speech speed for tts Python APIs by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/384
• Fix splitting utf8 string into words by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/385

Full Changelog: https://github.com/k2-fsa/sherpa-onnx/compare/v1.8.4...v1.8.5

What's Changed

• Fix CI for pip install by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/371
• Fix CI test for Go. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/372
• Add C API for offline TTS. by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/373
• Test go inside sherpa-onnx by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/374
• Add ccache to CI by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/375
• Support printing input text and words after splitting by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/376
• Add Go API for TTS by @csukuangfj in https://github.com/k2-fsa/sherpa-onnx/pull/377

Full Changelog: https://github.com/k2-fsa/sherpa-onnx/compare/v1.8.3...v1.8.4