Hassan Kazi c65f321699 Fix decoder positions of generated tokens in Canary greedy search (#4097) ...

The prompt is fed at positions 0..n-1, but generated tokens were fed at
1, 2, ... instead of n, n+1, ..., overlapping the prompt. Feed them at
decoder_input.size() + i - 1, as NeMo's GreedySequenceGenerator does.

Fixes #4096

2026-10-24 16:50:59 +08:00

..

3dspeaker

Upload speaker embedding models to huggingface (#1428)

2024-10-14 16:20:00 +08:00

apk

Remove espeak-ng and piper-phonemize from sherpa-onnx (#4055)

2026-10-20 11:09:04 +08:00

bbpe

Support hotwords with byte level bpe (#2802)

2025-11-19 18:21:16 +08:00

benchmark

Whisper timestamps (#2945)

2026-02-05 13:10:37 +08:00

ced

Support onnxruntime 1.18.0 (#906)

2024-07-10 17:05:26 +08:00

dart

Add tests for the windows arm64 npm package (#4069)

2026-10-20 15:42:34 +08:00

dotnet

Widen VAD sample positions to int64_t to fix long-stream SIGSEGV. (#4079)

2026-10-22 23:39:59 +08:00

go

Release v2.0.0 (#4090)

2026-10-23 20:32:33 +08:00

gtcrn

Add C++ runtime for silero_vad with RKNN (#2078)

2025-04-01 15:56:56 +08:00

hap

Add microphone demo about VAD+ASR for HarmonyOS (#1581)

2024-11-30 15:23:45 +08:00

icefall

Add pre-trained models for the Libriheavy dataset (#1122)

2024-07-13 19:21:13 +08:00

kitten-tts

Generate KittenTTS samples (#3607)

2026-05-12 21:54:32 +08:00

kokoro

Add conversion scripts for 7M Kokoro distills (Arabic + English) (#3954)

2026-09-17 16:17:22 +08:00

lazarus

Fix building for Pascal (#2305)

2025-06-20 11:10:07 +08:00

matcha-tts

Upload matcha tts zh-en model (#2865)

2025-12-05 11:45:41 +08:00

medasr

Add C++ runtime and Python API for Google MedASR models (#2935)

2025-12-25 17:25:56 +08:00

melo-tts

Fix(csrc/melotts): Fix V-words pronounciation on MeloTTS_en (#3002)

2026-01-07 17:27:45 +08:00

mobile-asr-models

Set batch size to 1 for more streaming ASR models (#1280)

2024-08-23 11:06:55 +08:00

moonshine

Export Moonshine ASR models to QNN (#3756)

2026-07-13 16:12:29 +08:00

nemo

Fix decoder positions of generated tokens in Canary greedy search (#4097)

2026-10-24 16:50:59 +08:00

node-addon-api

Widen VAD sample positions to int64_t to fix long-stream SIGSEGV. (#4079)

2026-10-22 23:39:59 +08:00

nodejs

Disable pthread support in WebAssembly. (#3836)

2026-08-04 10:06:58 +08:00

omnilingual-asr

Export omnilingualASR v2 (#3140)

2026-02-05 12:36:31 +08:00

paraformer

Fix typos in the project (#3293)

2026-03-12 11:10:55 +08:00

peng-cheng-starling

Add PengChengStarling models to sherpa-onnx (#1835)

2025-02-10 18:23:40 +08:00

piper

Upload vits-piper-pt_BR-cadu-medium to huggingface (#3763)

2026-07-15 16:55:00 +08:00

pocket-tts

Support BPE tokenizer (#3078)

2026-01-26 10:34:49 +08:00

pyannote/segmentation

Support https://huggingface.co/Revai/reverb-diarization-v1 (#1437)

2024-10-17 11:58:14 +08:00

qnn

Load QNN context binary for faster startup (#2877)

2025-12-09 17:55:19 +08:00

sense-voice

Fix typos in the project (#3293)

2026-03-12 11:10:55 +08:00

silero_vad/v4

Add C++ runtime for silero_vad with RKNN (#2078)

2025-04-01 15:56:56 +08:00

spleeter

Fix typos in the project (#3293)

2026-03-12 11:10:55 +08:00

supertonic

Fix dropped diacritics in Supertonic TTS text frontend (#3750)

2026-07-20 14:30:39 +08:00

t-one

Add C++ and Python support for T-one streaming Russian ASR models (#2575)

2025-09-09 12:07:34 +08:00

tauri

Export nvidia/parakeet-unified-en-0.6b to sherpa-onnx (#3556)

2026-04-27 16:38:53 +08:00

tele-speech

scale value fix (#1006)

2024-06-14 16:51:53 +08:00

uvr_mdx

Fix typos in the project. (#4073)

2026-10-21 09:57:49 +08:00

vits

Add Android demo for Inflect TTS (#3811)

2026-07-28 17:04:22 +08:00

vocos

Export vocos to sherpa-onnx (#2012)

2025-03-17 09:19:50 +08:00

wasm

Add tests for the windows arm64 npm package (#4069)

2026-10-20 15:42:34 +08:00

wenet

Fix padding bug in test-onnx-streaming.py (#3318)

2026-03-13 16:56:59 +08:00

wespeaker

Fix CI tests. (#898)

2024-05-21 20:37:29 +08:00

wheel

Fix publishing flutter packages (#4091)

2026-10-23 23:48:11 +08:00

whisper

Export Whisper models to QNN (#3697)

2026-06-24 09:44:13 +08:00

zipformer-ctc/ascend/2025-07-03

Export zipformer ctc models to Ascend NPU (#2824)

2025-11-25 14:56:35 +08:00

zipformer-transducer

Add Android QNN demo for non-streaming zipformer with Reazonspeech (#3670)

2026-06-12 09:44:33 +08:00

zipvoice/zh-en

Add script for testing zipvoice onnx models (#2887)

2025-12-11 14:26:18 +08:00

check_style_cpplint.sh

Support Supertonic 3 TTS (#3605)

2026-05-13 09:21:45 +08:00

export_bpe_vocab.py

Fix #1901: UnicodeEncodeError running export_bpe_vocab.py (#1902)

2025-02-21 06:29:28 +08:00

text2token.py

Fix typos in the project (#3293)

2026-03-12 11:10:55 +08:00

utils.sh

Refactor the code (#15)

2022-10-12 21:35:07 +08:00