0 Fork 0

mirror of https://github.com/k2-fsa/sherpa-onnx.git synced 2026-11-12 05:50:53 +08:00

Files

T

Joe Cheng 7be9a38e27 Whisper timestamps (#2945 )

This pull request significantly enhances the Whisper integration by introducing comprehensive timestamping capabilities. It provides both fine-grained token-level timestamps, derived from cross-attention weights using Dynamic Time Warping, and broader segment-level timestamps, based on Whisper's native timestamp tokens. This allows for more detailed temporal alignment of transcribed text with audio, which is crucial for applications like subtitle generation and improving the handling of long audio inputs. The changes span model export utilities, core C++ logic, and Python API bindings to fully support these new features.

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

web

Support TDNN models from the yesno recipe from icefall (#262 )

2023-08-12 19:50:22 +08:00

add-punctuation-online.py

Add Python binding for online punctuation models (#1312 )

2024-09-09 10:26:53 +08:00

add-punctuation.py

Add Python API for punctuation models. (#762 )

2024-04-13 13:28:17 +08:00

audio-tagging-from-a-file-ced.py

Add Python API example for CED audio tagging. (#793 )

2024-04-19 18:33:18 +08:00

audio-tagging-from-a-file.py

Add Python API and Python examples for audio tagging (#753 )

2024-04-11 11:12:48 +08:00

generate-subtitles.py

Add Parakeet TDT model for generating subtitles (#2649 )

2025-10-07 13:39:11 +08:00

http_server.py

add streaming-server with web client (#164 )

2023-05-30 22:46:52 +08:00

inverse-text-normalization-offline-asr.py

Support onnxruntime 1.18.0 (#906 )

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

inverse-text-normalization-online-asr.py

Add inverse text normalization for online ASR (#1020 )

2024-06-17 18:39:23 +08:00

keyword-spotter-from-microphone.py

Fix keyword spotting. (#1689 )

2025-01-20 16:41:10 +08:00

keyword-spotter.py

Fix keyword spotting. (#1689 )

2025-01-20 16:41:10 +08:00

non_streaming_server.py

Modify the model used (#1855 )

2025-02-13 15:08:04 +08:00

offline-decode-files.py

Add LODR support to online and offline recognizers (#2026 )

2025-07-09 16:23:46 +08:00

offline-dolphin-ctc-decode-files.py

Add C++ and Python API for Dolphin CTC models (#2085 )

2025-04-02 19:09:00 +08:00

offline-fire-red-asr-decode-files.py

Add C++ and Python API for Omnilingual ASR models. (#2772 )

2025-11-13 12:25:30 +08:00

offline-funasr-nano-decode-files.py

Add hotword support for FunASR-Nano (#3122 )

2026-02-04 18:05:38 +08:00

offline-medasr-ctc-decode-files.py

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

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

offline-moonshine-decode-files.py

Add C++ and Python API for Omnilingual ASR models. (#2772 )

2025-11-13 12:25:30 +08:00

offline-nemo-canary-decode-files.py

Add C++ and Python API for Omnilingual ASR models. (#2772 )

2025-11-13 12:25:30 +08:00

offline-nemo-ctc-decode-files.py

Add C++ runtime for non-streaming faster conformer transducer from NeMo. (#854 )

2024-05-10 12:15:39 +08:00

offline-nemo-parakeet-decode-file.py

Add C++ and Python API for Omnilingual ASR models. (#2772 )

2025-11-13 12:25:30 +08:00

offline-nemo-transducer-decode-files.py

Add C++ runtime for non-streaming faster conformer transducer from NeMo. (#854 )

2024-05-10 12:15:39 +08:00

offline-omnilingual-asr-ctc-decode-files.py

Add C++ and Python API for Omnilingual ASR models. (#2772 )

2025-11-13 12:25:30 +08:00

offline-omnilingual-asr-ctc-v2-decode-files.py

feat: add support for Meta Omnilingual ASR v2 models (#3138 )

2026-02-05 12:34:19 +08:00

offline-sense-voice-ctc-decode-files-with-hr.py

Remove cppjieba (#2664 )

2025-10-10 10:54:32 +08:00

offline-sense-voice-ctc-decode-files.py

Add C++ and Python API for Omnilingual ASR models. (#2772 )

2025-11-13 12:25:30 +08:00

offline-source-separation-spleeter.py

Add Python API for source separation (#2283 )

2025-06-05 20:44:26 +08:00

offline-source-separation-uvr.py

Add Python API for source separation (#2283 )

2025-06-05 20:44:26 +08:00

offline-speaker-diarization.py

Alex/feat add python example (#2490 )

2025-08-14 20:44:38 +08:00

offline-speech-enhancement-gtcrn.py

Add Python API for speech enhancement GTCRN models (#1978 )

2025-03-10 19:02:17 +08:00

offline-telespeech-ctc-decode-files.py

Add C++ runtime for Tele-AI/TeleSpeech-ASR (#970 )

2024-06-05 00:26:40 +08:00

offline-tts-play.py

Remove cppjieba (#2664 )

2025-10-10 10:54:32 +08:00

offline-tts.py

Remove cppjieba (#2664 )

2025-10-10 10:54:32 +08:00

offline-websocket-client-decode-files-paralell.py

Add non-streaming websocket server for python (#259 )

2023-08-11 15:56:24 +08:00

offline-websocket-client-decode-files-sequential.py

Add non-streaming websocket server for python (#259 )

2023-08-11 15:56:24 +08:00

offline-whisper-decode-files.py

Add C++ and Python API for Omnilingual ASR models. (#2772 )

2025-11-13 12:25:30 +08:00

offline-zeroshot-tts.py

Use a shorter name for Zipvoice models. (#2894 )

2025-12-11 20:30:19 +08:00

offline-zipformer-ctc-decode-files.py

Support non-streaming zipformer CTC ASR models (#2340 )

2025-07-04 15:57:07 +08:00

online-decode-files.py

Add LODR support to online and offline recognizers (#2026 )

2025-07-09 16:23:46 +08:00

online-nemo-ctc-decode-files.py

Add C++ support for streaming NeMo CTC models. (#857 )

2024-05-10 16:26:43 +08:00

online-t-one-ctc-decode-files.py

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

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

online-websocket-client-decode-file.py

Support streaming zipformer CTC (#496 )

2023-12-22 13:46:33 +08:00

online-websocket-client-microphone.py

Add non-streaming websocket server for python (#259 )

2023-08-11 15:56:24 +08:00

online-zipformer-ctc-hlg-decode-file.py

Add HLG decoding for streaming CTC models (#731 )

2024-04-03 21:31:42 +08:00

pocket-tts-play.py

Add CI for PocketTTS. (#3090 )

2026-01-27 12:10:05 +08:00

pocket-tts.py

Add CI for PocketTTS. (#3090 )

2026-01-27 12:10:05 +08:00

README.md

Add VAD + Non-streaming ASR Python example. (#332 )

2023-09-22 11:53:47 +08:00

simulate-streaming-paraformer-microphone.py

Add simulate streaming ASR Python example for Paraformer (#2839 )

2025-12-01 11:54:11 +08:00

simulate-streaming-sense-voice-microphone.py

Remove cppjieba (#2664 )

2025-10-10 10:54:32 +08:00

speaker-identification-with-vad-dynamic.py

Add Java/Kotlin API and Android support for ten-vad (#2389 )

2025-07-12 19:55:37 +08:00

speaker-identification-with-vad-non-streaming-asr-alsa.py

Add C++ and Python API for Omnilingual ASR models. (#2772 )

2025-11-13 12:25:30 +08:00

speaker-identification-with-vad-non-streaming-asr.py

Add Java/Kotlin API and Android support for ten-vad (#2389 )

2025-07-12 19:55:37 +08:00

speaker-identification-with-vad.py

Add Java/Kotlin API and Android support for ten-vad (#2389 )

2025-07-12 19:55:37 +08:00

speaker-identification.py

Replace torchaudio with soundfile in python-api-examples (#765 )

2024-04-13 23:39:07 +08:00

speech-recognition-from-microphone-with-endpoint-detection-alsa.py

Remove cppjieba (#2664 )

2025-10-10 10:54:32 +08:00

speech-recognition-from-microphone-with-endpoint-detection.py

Remove cppjieba (#2664 )

2025-10-10 10:54:32 +08:00

speech-recognition-from-microphone.py

Remove cppjieba (#2664 )

2025-10-10 10:54:32 +08:00

speech-recognition-from-url.py

Remove cppjieba (#2664 )

2025-10-10 10:54:32 +08:00

spoken-language-identification.py

Support spoken language identification with whisper (#694 )

2024-03-24 22:57:00 +08:00

streaming_server.py

'update20241203' (#1589 )

2024-12-04 09:22:24 +08:00

streaming-paraformer-asr-microphone.py

Fix displaying streaming speech recognition results for Python. (#2196 )

2025-05-09 21:48:49 +08:00

test-sentence-piece-tokenizer.py

Support BPE tokenizer (#3078 )

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

test-whisper-timestamps.py

Whisper timestamps (#2945 )

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

two-pass-speech-recognition-from-microphone.py

Fix displaying streaming speech recognition results for Python. (#2196 )

2025-05-09 21:48:49 +08:00

two-pass-wss.py

Add C++ and Python API for Omnilingual ASR models. (#2772 )

2025-11-13 12:25:30 +08:00

vad-alsa.py

Add Java/Kotlin API and Android support for ten-vad (#2389 )

2025-07-12 19:55:37 +08:00

vad-microphone.py

Add Java/Kotlin API and Android support for ten-vad (#2389 )

2025-07-12 19:55:37 +08:00

vad-remove-non-speech-segments-alsa.py

Add Java/Kotlin API and Android support for ten-vad (#2389 )

2025-07-12 19:55:37 +08:00

vad-remove-non-speech-segments-from-file.py

Add Java/Kotlin API and Android support for ten-vad (#2389 )

2025-07-12 19:55:37 +08:00

vad-remove-non-speech-segments.py

Add Java/Kotlin API and Android support for ten-vad (#2389 )

2025-07-12 19:55:37 +08:00

vad-with-non-streaming-asr.py

Remove cppjieba (#2664 )

2025-10-10 10:54:32 +08:00

README.md

File description

./http_server.py It defines which files to server. Files are saved in ./web.
non_streaming_server.py WebSocket server for non-streaming models.
vad-remove-non-speech-segments.py It uses silero-vad to remove non-speech segments and concatenate all speech segments into a single one.
vad-with-non-streaming-asr.py It shows how to use VAD with a non-streaming ASR model for speech recognition from a microphone