v1.10.36

What's Changed

• Update AAR version in Android Java demo by @csukuangfj in #1618
• Support linking onnxruntime statically for Android by @csukuangfj in #1619
• Update readme to include Open-LLM-VTuber by @csukuangfj in #1622
• Fixing typos in node examples by @sawich in #1625
• Support using onnxruntime 1.16.0 with CUDA 11.4 on Jetson Orin NX (Linux arm64 GPU). by @csukuangfj in #1630
• Update readme to include jetson orin nx and nano b01 by @csukuangfj in #1631
• feat: add checksum action by @thewh1teagle in #1632
• Support decoding with byte-level BPE (bbpe) models. by @csukuangfj in #1633
• feat: enable c api for android ci by @thewh1teagle in #1635
• Update README.md by @Humorousf in #1640
• SherpaOnnxVadAsr: Offload runSecondPass to background thread for improved real-time audio processing by @rominf in #1638
• Fix GitHub actions. by @csukuangfj in #1642
• Release v1.10.36 by @csukuangfj in #1643

New Contributors

• @sawich made their first contribution in #1625
• @Humorousf made their first contribution in #1640
• @rominf made their first contribution in #1638

Full Changelog: v1.10.35...v1.10.36

v1.10.35

What's Changed

• Add missing changes about speaker identfication demo for HarmonyOS by @csukuangfj in #1612
• Provide sherpa-onnx.aar for Android by @csukuangfj in #1615
• Use aar in Android Java demo. by @csukuangfj in #1616
• 🔧 build(portaudio-go): Fixed version 1.0.3 by @deretame in #1614
• Release v1.10.35 by @csukuangfj in #1617

New Contributors

• @deretame made their first contribution in #1614

Full Changelog: v1.10.34...v1.10.35

v1.10.34

What's Changed

• Fix building node-addon package by @csukuangfj in #1598
• Update doc links for HarmonyOS by @csukuangfj in #1601
• Add on-device real-time ASR demo for HarmonyOS by @csukuangfj in #1606
• Add speaker identification APIs for HarmonyOS by @csukuangfj in #1607
• Add speaker identification demo for HarmonyOS by @csukuangfj in #1608
• Add speaker diarization API for HarmonyOS. by @csukuangfj in #1609
• Add speaker diarization demo for HarmonyOS by @csukuangfj in #1610
• Release v1.10.34 by @csukuangfj in #1611

Full Changelog: v1.10.33...v1.10.34

v1.10.33

What's Changed

• Add non-streaming ASR support for HarmonyOS. by @csukuangfj in #1564
• Add streaming ASR support for HarmonyOS. by @csukuangfj in #1565
• fix building for Android by @csukuangfj in #1568
• Publish sherpa_onnx.har for HarmonyOS by @csukuangfj in #1572
• Add VAD+ASR demo for HarmonyOS by @csukuangfj in #1573
• Fix publishing har packages for HarmonyOS by @csukuangfj in #1576
• Add CI to build HAPs for HarmonyOS by @csukuangfj in #1578
• Add microphone demo about VAD+ASR for HarmonyOS by @csukuangfj in #1581
• Fix getting microphone permission for HarmonyOS VAD+ASR example by @csukuangfj in #1582
• Add HarmonyOS support for text-to-speech. by @csukuangfj in #1584
• fix: support both old and new websockets request headers format by @JiayuXu0 in #1588
• add '--modeling-unit' and "--bpe-vocab" to /sherpa-onnx/python-api-examples/streaming_server.py by @goddamnVincent in #1589
• Add on-device tex-to-speech (TTS) demo for HarmonyOS by @csukuangfj in #1590
• Release v1.10.33 by @csukuangfj in #1591

New Contributors

• @JiayuXu0 made their first contribution in #1588
• @goddamnVincent made their first contribution in #1589

Full Changelog: v1.10.32...v1.10.33

v1.10.32

What's Changed

• Support cross-compiling for HarmonyOS by @csukuangfj in #1553
• HarmonyOS support for VAD. by @csukuangfj in #1561
• Fix flutter ios by @csukuangfj in #1563

Full Changelog: v1.10.31...v1.10.32

v1.10.31

What's Changed

• Publish pre-built wheels for Python 3.13 by @csukuangfj in #1485
• Add some frequently used ASR models to README.md by @csukuangfj in #1486
• fix typo by @pengzhendong in #1488
• Publish pre-built macos xcframework by @csukuangfj in #1490
• Removed unused TTS example code in .Net examples by @csukuangfj in #1492
• Update pybind11 to support numpy 2.0 by @csukuangfj in #1493
• Fix reading tokens.txt on Windows. by @csukuangfj in #1497
• Add two-pass ASR Android APKs for Moonshine models. by @csukuangfj in #1499
• Support building GPU-capable sherpa-onnx on Linux aarch64. by @csukuangfj in #1500
• Add an example for computing RTF about streaming ASR. by @csukuangfj in #1501
• Publish pre-built wheels with CUDA support for Linux aarch64. by @csukuangfj in #1507
• Fix building by @csukuangfj in #1508
• Export the English TTS model from MeloTTS by @csukuangfj in #1509
• Reduce vad-sense-voice example code. by @whyb in #1510
• Fix: Reset sample-buffer after processing by @iteamvep in #1521
• Fixes #1512 by @csukuangfj in #1522
• Revert: [#1521] No need to reset sample-buffer by @iteamvep in #1524
• Add Lazarus example for Moonshine models. by @csukuangfj in #1532
• 增加isolate_tts demo by @Spicely in #1529
• Add WebAssembly example for VAD + Moonshine models. by @csukuangfj in #1535
• Add Android APK for streaming Paraformer ASR by @csukuangfj in #1538
• Support static build for windows arm64. by @csukuangfj in #1539
• fix windows build by @endink in #1546
• Use xcframework for Flutter iOS plugin. by @csukuangfj in #1547

New Contributors

• @whyb made their first contribution in #1510
• @iteamvep made their first contribution in #1521
• @Spicely made their first contribution in #1529
• @endink made their first contribution in #1546

Full Changelog: v1.10.30...v1.10.31

v1.10.30

What's Changed

• Fix building node-addon for Windows x86. by @csukuangfj in #1469
• Begin to support https://github.com/usefulsensors/moonshine by @csukuangfj in #1470
• Publish pre-built JNI libs for Linux aarch64 by @csukuangfj in #1472
• Add C++ runtime and Python APIs for Moonshine models by @csukuangfj in #1473
• Add Kotlin and Java API for Moonshine models by @csukuangfj in #1474
• Add C and C++ API for Moonshine models by @csukuangfj in #1476
• Add Swift API for Moonshine models. by @csukuangfj in #1477
• Add Go API examples for adding punctuations to text. by @csukuangfj in #1478
• Add Go API for Moonshine models by @csukuangfj in #1479
• Add JavaScript API for Moonshine models by @csukuangfj in #1480
• Add Dart API for Moonshine models. by @csukuangfj in #1481
• Add Pascal API for Moonshine models by @csukuangfj in #1482
• Add C# API for Moonshine models. by @csukuangfj in #1483
• Release v1.10.30 by @csukuangfj in #1484

Full Changelog: v1.10.29...v1.10.30

v1.10.29

What's Changed

• Upload speaker embedding models to huggingface by @csukuangfj in #1428
• "Speaker identification" is repeat! by @semxum in #1431
• Add Go API for offline punctuation models by @csukuangfj in #1434
• updated onnxruntime-linux-aarch64.cmake so that libonnxruntime.so can… by @shawl336 in #1436
• Support https://huggingface.co/Revai/reverb-diarization-v1 by @csukuangfj in #1437
• fix "log10" compile error by import CMATH lib by @Zazzle516 in #1438
• add more models for speaker diarization by @csukuangfj in #1440
• Add Java API example for hotwords. by @csukuangfj in #1442
• update java for hotword jar by @YeyuchenBa in #1444
• add java android demo by @JameWade in #1454
• Add C++ API for streaming ASR. by @csukuangfj in #1455
• Add C++ API for non-streaming ASR by @csukuangfj in #1456
• Fix style issues by @csukuangfj in #1458
• Handle NaN embeddings in speaker diarization. by @csukuangfj in #1461
• Add speaker identification with VAD and non-streaming ASR using ALSA by @Peakyxh in #1463
• Support GigaAM CTC models for Russian ASR by @csukuangfj in #1464
• Add GigaAM NeMo transducer model for Russian ASR by @csukuangfj in #1467
• Release v1.10.29 by @csukuangfj in #1468

New Contributors

• @semxum made their first contribution in #1431
• @Zazzle516 made their first contribution in #1438
• @YeyuchenBa made their first contribution in #1444
• @JameWade made their first contribution in #1454
• @Peakyxh made their first contribution in #1463

Full Changelog: v1.10.28...v1.10.29

v1.10.28

What's Changed

• Fix swift example for generating subtitles. by @csukuangfj in #1362
• allow more online models to load tokens file from the memory by @shawl336 in #1352
• Fix CI errors introduced by supporting loading keywords from buffers by @csukuangfj in #1366
• Update online_model.dart by @flutter-painter in #1375
• Fix running MeloTTS models on GPU. by @csukuangfj in #1379
• Support Parakeet models from NeMo by @csukuangfj in #1381
• Export Pyannote speaker segmentation models to onnx by @csukuangfj in #1382
• Support Agglomerative clustering. by @csukuangfj in #1384
• Add Python API for clustering by @csukuangfj in #1385
• support whisper turbo by @csukuangfj in #1390
• Potentially fixes segmentation fault in online decoding with hotwords by @vsd-vector in #1393
• Speaker diarization example with onnxruntime Python API by @csukuangfj in #1395
• C++ API for speaker diarization by @csukuangfj in #1396
• Python API for speaker diarization. by @csukuangfj in #1400
• C API for speaker diarization by @csukuangfj in #1402
• docs(nodejs-addon-examples): add guide for pnpm user by @YogiLiu in #1401
• Go API for speaker diarization by @csukuangfj in #1403
• Swift API for speaker diarization by @csukuangfj in #1404
• Update readme to include more external projects using sherpa-onnx by @csukuangfj in #1405
• C# API for speaker diarization by @csukuangfj in #1407
• JavaScript API (node-addon) for speaker diarization by @csukuangfj in #1408
• WebAssembly exmaple for speaker diarization by @csukuangfj in #1411
• Handle audio files less than 10s for speaker diarization. by @csukuangfj in #1412
• JavaScript API with WebAssembly for speaker diarization by @csukuangfj in #1414
• Kotlin API for speaker diarization by @csukuangfj in #1415
• Java API for speaker diarization by @csukuangfj in #1416
• Dart API for speaker diarization by @csukuangfj in #1418
• Pascal API for speaker diarization by @csukuangfj in #1420
• Android JNI support for speaker diarization by @csukuangfj in #1421
• Android demo for speaker diarization by @csukuangfj in #1423
• Release v1.10.28 by @csukuangfj in #1424

New Contributors

• @flutter-painter made their first contribution in #1375
• @YogiLiu made their first contribution in #1401

Full Changelog: v1.10.27...v1.10.28

speaker-segmentation-models

Please see
https://k2-fsa.github.io/sherpa/onnx/speaker-diarization/index.html