mirror of
https://github.com/k2-fsa/sherpa-onnx.git
synced 2026-11-10 21:11:03 +08:00
Fangjun Kuang
f2e01fe8e3
Fixes #3635 It is for v2.0.0 and breaks the ABI. CircularBuffer::head_ and tail_ are absolute sample counters that grow forever. As int32_t they overflow after 2^31 samples (~37 h at 16 kHz); tail_ % capacity then goes negative and std::copy() writes to an invalid iterator, crashing long-running VAD streams. Widen every absolute stream position to int64_t. Counts and capacities (Push/Pop/Get's n, Size(), capacity) stay int32_t — they are bounded by buffer memory, not stream duration.
Introduction
This directory contains examples for the JAVA API of sherpa-onnx.
Supported platforms
| OS | Architecture | Status |
|---|---|---|
| Linux | x64 | ✅ |
| Linux | ARM64 | ✅ |
| macOS | x64 (Intel) | ✅ |
| macOS | ARM64 (Apple Silicon) | ✅ |
| Windows | x64 | ✅ |
| Windows | ARM64 | ✅ |
Usage
Non-streaming speech enhancement
./run-non-streaming-speech-enhancement-gtcrn.sh
./run-non-streaming-speech-enhancement-dpdfnet.sh
Use 16 kHz DPDFNet models such as
dpdfnet_baseline.onnx, dpdfnet2.onnx, dpdfnet4.onnx, or dpdfnet8.onnx for
downstream ASR and dpdfnet2_48khz_hr.onnx for 48 kHz enhancement output.
Non-streaming speaker diarization
./run-offline-speaker-diarization.sh
Streaming Speech recognition
./run-streaming-asr-from-mic-transducer.sh
./run-streaming-decode-file-ctc-hlg.sh
./run-streaming-decode-file-ctc.sh
./run-streaming-decode-file-paraformer.sh
./run-streaming-decode-file-tone-ctc.sh
./run-streaming-decode-file-transducer.sh
Non-Streaming Speech recognition
./run-non-streaming-decode-file-dolphin-ctc.sh
./run-non-streaming-decode-file-fire-red-asr-ctc.sh
./run-non-streaming-decode-file-fire-red-asr.sh
./run-non-streaming-decode-file-funasr-nano.sh
./run-non-streaming-decode-file-medasr-ctc.sh
./run-non-streaming-decode-file-moonshine.sh
./run-non-streaming-decode-file-moonshine-v2.sh
./run-non-streaming-decode-file-nemo-canary.sh
./run-non-streaming-decode-file-nemo.sh
./run-non-streaming-decode-file-omnilingual-asr-ctc.sh
./run-non-streaming-decode-file-paraformer.sh
./run-non-streaming-decode-file-sense-voice-with-hr.sh
./run-non-streaming-decode-file-sense-voice.sh
./run-non-streaming-decode-file-tele-speech-ctc.sh
./run-non-streaming-decode-file-transducer-hotwords.sh
./run-non-streaming-decode-file-transducer.sh
./run-non-streaming-decode-file-wenet-ctc.sh
./run-non-streaming-decode-file-whisper-multiple.sh
./run-non-streaming-decode-file-whisper.sh
./run-non-streaming-decode-file-zipformer-ctc.sh
Non-Streaming Speech recognition with homophone replacer
./run-non-streaming-decode-file-sense-voice-with-hr.sh
Non-Streaming text-to-speech
./run-non-streaming-tts-coqui-de.sh
./run-non-streaming-tts-kitten-en-lexicon.sh
./run-non-streaming-tts-kokoro-en-lexicon.sh
./run-non-streaming-tts-kokoro-zh-en-lexicon.sh
./run-non-streaming-tts-matcha-en-lexicon.sh
./run-non-streaming-tts-matcha-zh-lexicon.sh
./run-non-streaming-tts-piper-en-with-callback-lexicon.sh
./run-non-streaming-tts-piper-en-lexicon.sh
./run-non-streaming-tts-vits-zh-lexicon.sh
./run-pocket-tts.sh
./run-zipvoice-tts-lexicon.sh
Non-Streaming text-to-speech (Playback the audio as it is being generated)
./run-non-streaming-tts-piper-en-with-callback-lexicon.sh
Spoken language identification
./run-spoken-language-identification-whisper.sh
Add punctuations to text
The punctuation model supports both English and Chinese.
./run-offline-add-punctuation-zh-en.sh
./run-online-add-punctuation-zh-en.sh
Audio tagging
./run-audio-tagging-zipformer-from-file.sh
./run-audio-tagging-ced-from-file.sh
Speaker identification
./run-speaker-identification.sh
VAD with a microphone
./run-vad-from-mic.sh
VAD with a microphone + Non-streaming SenseVoice for speech recognition
./run-vad-from-mic-non-streaming-sense-voice.sh
VAD with a microphone + Non-streaming Paraformer for speech recognition
./run-vad-from-mic-non-streaming-paraformer.sh
VAD with a microphone + Non-streaming Whisper tiny.en for speech recognition
./run-vad-from-mic-non-streaming-whisper.sh
VAD (Remove silence)
./run-vad-remove-silence.sh
./run-ten-vad-remove-silence.sh
VAD + Non-streaming Dolphin CTC for speech recognition
./run-vad-non-streaming-dolphin-ctc.sh
VAD + Non-streaming SenseVoice for speech recognition
./run-vad-non-streaming-sense-voice.sh
VAD + Non-streaming Paraformer for speech recognition
./run-vad-non-streaming-paraformer.sh
Keyword spotter
./run-kws-from-file.sh