v1.12.15

What's Changed

• exposing online punctuation model support in node-addon-api by @colourmebrad in #2609
• Fix building wheels by @csukuangfj in #2619
• Export one more Piper Arabic TTS model by @csukuangfj in #2623
• fix: hot update language for sencevoice by @o-u-p in #2627
• develop zipvoice c-api by @BarryKCL in #2628
• Add CI tests for Zipvoice Go API by @csukuangfj in #2630
• Remove hardcoded dithering value in NeMo transducer recognizer by @vsd-vector in #2639
• Reduce verbose output about reading lexicon for TTS by @csukuangfj in #2648
• Add Parakeet TDT model for generating subtitles by @csukuangfj in #2649
• Add more Piper TTS models by @csukuangfj in #2651
• Add CXX API for audio tagging by @csukuangfj in #2652
• Add C# API for audio tagging by @csukuangfj in #2653
• Support KWS + RKNN. by @csukuangfj in #2190
• Support https://github.com/ASLP-lab/WenetSpeech-Chuan by @csukuangfj in #2656
• Fix building for android by @csukuangfj in #2657
• Fix ios build script by @vovasty in #2645
• Update kaldi-native-fbank by @csukuangfj in #2659
• Add missing python class definitions for builds without TTS support by @ius in #2660
• Refactor JNI by @csukuangfj in #2661
• Remove jieba from kokoro and matcha tts. by @csukuangfj in #2662
• add flet_sherpa_onnx in readme by @SamYuan1990 in #2663
• Remove cppjieba by @csukuangfj in #2664
• Add phrase matcher to merge words into phrases for TTS. by @csukuangfj in #2668
• Limit number of tokens per sentence in MatchaTTS. by @csukuangfj in #2671
• Update README to include a ROS2 project using sherpa-onnx by @csukuangfj in #2672
• Fix building Flutter APPs by @csukuangfj in #2673
• Export Paraformer to RKNN by @csukuangfj in #2689
• Update README.md add achatbot-go Projects using sherpa-onnx link by @weedge in #2691
• Add CI to export Paraformer to RKNN by @csukuangfj in #2692
• Support MatchTTS with English and Chinese by @csukuangfj in #2695
• Export Paraformer ASR models from FunASR to Ascend NPU 910B by @csukuangfj in #2697
• Update README to include Ascend NPU by @csukuangfj in #2698
• Fix WASM (JS) after adding zipvoice. by @csukuangfj in #2702
• Export SenseVoice ASR models to Ascend NPU 910B by @csukuangfj in #2707
• Fix building for various language bindings after adding zipvoice by @csukuangfj in #2709
• Release v1.12.15 by @csukuangfj in #2710

New Contributors

• @colourmebrad made their first contribution in #2609
• @o-u-p made their first contribution in #2627
• @BarryKCL made their first contribution in #2628
• @vovasty made their first contribution in #2645
• @ius made their first contribution in #2660
• @SamYuan1990 made their first contribution in #2663
• @weedge made their first contribution in #2691

Full Changelog: v1.12.14...v1.12.15

v1.12.14

What's Changed

• Fix setting rknn core mask by @csukuangfj in #2594
• Add Dart API for spoken language identification by @kibsoft in #2596
• Add CI tests for dart spoken language identifcation example by @csukuangfj in #2598
• Provide pre-compiled shepra-onnx libs/binaries for CUDA 12.x + onnxruntime 1.22.0 by @csukuangfj in #2599
• Provide pre-compiled whls for cuda 12.x on Linux x64 and Windows x64 by @csukuangfj in #2601
• Fix TDT decoding for NeMo TDT transducers by @csukuangfj in #2606
• Add a C++ example for simulated streaming ASR by @csukuangfj in #2607
• Release v1.12.14 by @csukuangfj in #2608

New Contributors

• @kibsoft made their first contribution in #2596

Full Changelog: v1.12.13...v1.12.14

v1.12.13

What's Changed

• Fix initializing symbol table for OnlineRecognizer. by @csukuangfj in #2590
• Support RK NPU for SenseVoice non-streaming ASR models by @csukuangfj in #2589
• Upload RKNN models for sense-voice by @csukuangfj in #2592
• Release v1.12.13 by @csukuangfj in #2593

Full Changelog: v1.12.12...v1.12.13

v1.12.12

What's Changed

• Fix building for risc-v by @csukuangfj in #2549
• Fix using sherpa-onnx as a cmake sub-project. by @csukuangfj in #2550
• Update kaldifst and kaldi-decoder by @csukuangfj in #2551
• Bug fix-修复armv8l架构下的Android系统调用java-api时启动异常 by @fengin in #2556
• Disable loading libs from jar on Android. by @csukuangfj in #2557
• Fix cantonese vits tts by @csukuangfj in #2558
• Avoid appending blanks for Cantonese vits tts. by @csukuangfj in #2559
• Add hint for loading model files from SD card on Android. by @csukuangfj in #2564
• Update README to include https://github.com/Mentra-Community/MentraOS by @csukuangfj in #2565
• Export models from https://github.com/voicekit-team/T-one to sherpa-onnx by @csukuangfj in #2571
• Add C++ and Python support for T-one streaming Russian ASR models by @csukuangfj in #2575
• Add various language bindings for streaming T-one Russian ASR models by @csukuangfj in #2576
• Fix the missing online punctuation in android aar by @csukuangfj in #2577
• Export KittenTTS mini v0.1 to sherpa-onnx by @csukuangfj in #2578
• Upload new sense-voice models by @csukuangfj in #2580
• Export ASLP-lab/WSYue-ASR/tree/main/u2pp_conformer_yue to sherpa-onnx by @csukuangfj in #2582
• Add various languge bindings for Wenet non-streaming CTC models by @csukuangfj in #2584
• Release v1.12.12 by @csukuangfj in #2586

New Contributors

• @fengin made their first contribution in #2556

Full Changelog: v1.12.11...v1.12.12

v1.12.11

What's Changed

• Add two more Piper tts models by @csukuangfj in #2525
• Generate tts samples for MatchaTTS (English). by @csukuangfj in #2527
• Fix releasing go packages by @csukuangfj in #2529
• Add license info about tts models from OpenVoiceOS by @csukuangfj in #2530
• Support BPE models with byte fallback. by @csukuangfj in #2531
• Simplify the usage of our non-Android Java API by @csukuangfj in #2533
• Fix wasm for kws by @csukuangfj in #2535
• Add one more German tts model from OpenVoiceOS. by @csukuangfj in #2536
• Fix uploading win32 libs to huggingface by @csukuangfj in #2537
• Add Zipvoice by @pkufool in #2487
• Fix c api by @csukuangfj in #2545
• Fix linking by @csukuangfj in #2546
• Release 1.12.11 by @csukuangfj in #2547

Full Changelog: v1.12.10...v1.12.11

v1.12.10

What's Changed

• Add VOSK streaming Russian ASR models and Kroko streaming German ASR models by @csukuangfj in #2502
• Refactor CI tests by @csukuangfj in #2504
• Update APK versions by @csukuangfj in #2505
• Export whisper distil-large-v3 and distil-large-v3.5 to sherpa-onnx by @csukuangfj in #2506
• Support specifying pronunciations of phrases in Chinese TTS. by @csukuangfj in #2507
• fix(flutter): fix unicode problem in windows path by @twmht in #2508
• feat: add punctuation C++ API by @Aruxxxi in #2510
• fix ctrl+c may lead to coredump by @yangjuncode in #2511
• Add kitten tts nano v0.2 by @csukuangfj in #2512
• Scripts to generate tts samples by @csukuangfj in #2513
• Add tdt duration to APIs by @bradmurray-dt in #2514
• Support 16KB page size for Android by @csukuangfj in #2520
• Split sherpa-onnx Python package by @csukuangfj in #2521
• Fix kokoro tts for punctuations by @csukuangfj in #2522
• Release v1.12.10 by @csukuangfj in #2523

New Contributors

• @Aruxxxi made their first contribution in #2510
• @yangjuncode made their first contribution in #2511
• @bradmurray-dt made their first contribution in #2514

Full Changelog: v1.12.9...v1.12.10

v1.12.9

What's Changed

• Add more piper tts models by @csukuangfj in #2480
• Fix ASR for UE by @PeiloViolet in #2483
• push to maven center by @litongjava in #2463
• Specify ABIs when building APKs by @csukuangfj in #2488
• Add more debug info for vits tts by @csukuangfj in #2491
• Add Swift API for computing speaker embeddings by @csukuangfj in #2492
• Alex/feat add python example by @AlexWhisper in #2490
• Support TDT transducer decoding by @csukuangfj in #2495
• Fix java test by @csukuangfj in #2496
• Refactor Swift API by @csukuangfj in #2493
• add TtsReader app to README.md by @ys-pro-duction in #2498
• Export https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3 to sherpa-onnx by @csukuangfj in #2500
• Fix building apk by @csukuangfj in #2499
• Release v1.12.9 by @csukuangfj in #2501

New Contributors

• @PeiloViolet made their first contribution in #2483
• @litongjava made their first contribution in #2463
• @AlexWhisper made their first contribution in #2490
• @ys-pro-duction made their first contribution in #2498

Full Changelog: v1.12.8...v1.12.9

v1.12.8

What's Changed

• Expose JNI to compute probability of chunk in VAD by @twmht in #2433
• Support models from https://huggingface.co/Banafo/Kroko-ASR by @csukuangfj in #2453
• Add APIs for Online NeMo CTC models by @csukuangfj in #2454
• Export https://github.com/KittenML/KittenTTS to sherpa-onnx by @csukuangfj in #2456
• Fix punctuations in kokoro tts. by @csukuangfj in #2458
• Limit number of tokens in fire red asr decoding. by @csukuangfj in #2459
• Add C++ runtime for kitten-tts by @csukuangfj in #2460
• Add Kotlin and Java API for KittenTTS by @csukuangfj in #2461
• Add Android TTS Engine APK for KittenTTS by @csukuangfj in #2465
• Add Python API for KittenTTS. by @csukuangfj in #2466
• Add C API for KittenTTS by @csukuangfj in #2467
• Add CXX API for KittenTTS by @csukuangfj in #2469
• Add JavaScript API (node-addon) for KittenTTS by @csukuangfj in #2470
• Add JavaScript API (WebAssembly) for KittenTTS by @csukuangfj in #2471
• Add Pascal API for KittenTTS by @csukuangfj in #2474
• Add Dart API for KittenTTS by @csukuangfj in #2475
• Add Swift API for KittenTTS by @csukuangfj in #2476
• Add C# API for KittenTTS by @csukuangfj in #2477
• Add Go API for KittenTTS by @csukuangfj in #2478
• Release v1.12.8 by @csukuangfj in #2479

New Contributors

• @twmht made their first contribution in #2433

Full Changelog: v1.12.7...v1.12.8

v1.12.7

What's Changed

• Support Portuguese and German ASR models from NeMo by @csukuangfj in #2394
• Support returning the current speech segment for VAD. by @csukuangfj in #2397
• Add more piper tts polish models by @csukuangfj in #2403
• Support VAD+ASR for WearOS by @csukuangfj in #2404
• support test long audio with streaming-model & vad by @pingfengluo in #2405
• fix typo in sherpa-onnx-vad-with-online-asr.cc by @pingfengluo in #2407
• add tail padding for sherpa-onnx-vad-with-online-asr by @pingfengluo in #2408
• Add more French TTS models by @csukuangfj in #2424
• Add more piper tts models by @csukuangfj in #2425
• Implement max_symbols_per_frame for GigaAM2 by @nshmyrev in #2423
• Fix GigaAM transducer encoder output length data type by @csukuangfj in #2426
• Add friendly log messages for Android and HarmonyOS TTS users. by @csukuangfj in #2427
• fix setgraph in OnlineCtcFstDecoderConfig Java api by @njsyw1997 in #2411
• Release v1.12.7 by @csukuangfj in #2428

New Contributors

• @njsyw1997 made their first contribution in #2411

Full Changelog: v1.12.6...v1.12.7

v1.12.6

What's Changed

• Support silero-vad v4 exported by k2-fsa by @csukuangfj in #2372
• Support ten vad by @csukuangfj in #2377
• Fix compile errors for Linux by @csukuangfj in #2378
• Add C API for ten-vad by @csukuangfj in #2379
• Add CXX API examples for ten-vad. by @csukuangfj in #2380
• Add JavaScript (WebAssembly) API for ten-vad by @csukuangfj in #2382
• Add JavaScript (node-addon) API for ten-vad by @csukuangfj in #2383
• Add Go API for ten-vad by @csukuangfj in #2384
• Add C# API for ten-vad by @csukuangfj in #2385
• Add Dart API for ten-vad by @csukuangfj in #2386
• Add Swift API for ten-vad by @csukuangfj in #2387
• Add Pascal API for ten-vad by @csukuangfj in #2388
• Add Java/Kotlin API and Android support for ten-vad by @csukuangfj in #2389
• Release v1.12.6 by @csukuangfj in #2390

Full Changelog: v1.12.5...v1.12.6