mirror of
https://github.com/k2-fsa/sherpa-onnx.git
synced 2026-11-10 21:11:03 +08:00
Fangjun Kuang
0b3647632f
Fixes #3731 espeak-ng and piper-phonemize are no longer built into sherpa-onnx. Text frontends are now: - **lexicon** — built in, no extra dependency - **phonemize** — phonemize outside sherpa-onnx (e.g. [piper-phonemize](https://github.com/csukuangfj/piper-phonemize)) and pass the result in. That library is GPL, so it stays optional: sherpa-onnx is GPL-free after this PR. ## API - `SherpaOnnxGenerationConfig` gains `phoneme_codepoints` and `tokens` (mutually exclusive alternatives to `text`) - `data_dir` on the TTS model configs is deprecated and ignored; the ABI slot is kept - all bindings updated: C/C++, Python, Java, Kotlin, Go, Rust, C#, Swift, Pascal, Dart/Flutter, node-addon, WASM, HarmonyOS
281 lines
5.4 KiB
Bash
Executable File
281 lines
5.4 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
set -ex
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
source "$SCRIPT_DIR/common.sh"
|
|
cd dart-api-examples
|
|
|
|
echo '----------Version----------'
|
|
pushd version
|
|
./run.sh
|
|
popd
|
|
|
|
pushd tts
|
|
|
|
echo '----------tts----------'
|
|
./run-pocket-en.sh
|
|
./run-kitten-en-lexicon.sh
|
|
./run-kitten-en-phonemize.sh
|
|
./run-supertonic-en.sh
|
|
./run-kokoro-zh-en-lexicon.sh
|
|
./run-kokoro-en-lexicon.sh
|
|
./run-kokoro-en-phonemize.sh
|
|
./run-matcha-zh-lexicon.sh
|
|
./run-matcha-en-lexicon.sh
|
|
./run-matcha-en-phonemize.sh
|
|
./run-zipvoice-zh-en-lexicon.sh
|
|
ls -lh *.wav
|
|
rm -rf matcha-icefall-*
|
|
rm -rf sherpa-onnx-zipvoice-*
|
|
rm -f lexicon-en-us.txt
|
|
rm *.onnx
|
|
|
|
echo '----------piper tts----------'
|
|
./run-piper-lexicon.sh
|
|
./run-piper-phonemize.sh
|
|
rm -f lexicon-en-us.txt
|
|
rm -rf vits-piper-*
|
|
|
|
echo '----------german tts----------'
|
|
./run-vits-de-phonemize.sh
|
|
rm -rf vits-piper-*
|
|
|
|
echo '----------coqui tts----------'
|
|
./run-coqui.sh
|
|
rm -rf vits-coqui-*
|
|
|
|
echo '----------zh tts----------'
|
|
./run-vits-zh-lexicon.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
ls -lh *.wav
|
|
|
|
popd # tts
|
|
|
|
pushd non-streaming-asr
|
|
|
|
echo '----------Moonshine v2----------'
|
|
./run-moonshine-v2.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------Wenet CTC----------'
|
|
./run-wenet-ctc.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------Zipformer CTC----------'
|
|
./run-zipformer-ctc.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------Zipformer CTC HLG----------'
|
|
./run-zipformer-ctc-hlg.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------Cohere Transcribe----------'
|
|
./run-cohere-transcribe.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------Qwen3 ASR----------'
|
|
./run-qwen3-asr.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------FireRedASR CTC----------'
|
|
./run-fire-red-asr-ctc.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------FunASR Nano----------'
|
|
./run-funasr-nano.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------MedASR CTC----------'
|
|
./run-medasr-ctc.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------Omnilingual ASR CTC----------'
|
|
./run-omnilingual-asr-ctc.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------SenseVoice----------'
|
|
./run-sense-voice-with-hr.sh
|
|
./run-sense-voice.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------FireRedAsr----------'
|
|
./run-fire-red-asr.sh
|
|
rm -rf sherpa-onnx-fire-red-asr-*
|
|
|
|
echo '----------NeMo transducer----------'
|
|
./run-nemo-transducer.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------Dolphin CTC----------'
|
|
./run-dolphin-ctc.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------NeMo CTC----------'
|
|
./run-nemo-ctc.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------TeleSpeech CTC----------'
|
|
./run-telespeech-ctc.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------moonshine----------'
|
|
./run-moonshine.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------whisper----------'
|
|
./run-whisper.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------zipformer transducer----------'
|
|
./run-zipformer-transducer.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------paraformer itn----------'
|
|
./run-paraformer-itn.sh
|
|
|
|
echo '----------paraformer----------'
|
|
./run-paraformer.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------VAD with paraformer----------'
|
|
./run-vad-with-paraformer.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
popd # non-streaming-asr
|
|
|
|
pushd speech-enhancement-gtcrn
|
|
echo "speech enhancement with gtcrn models"
|
|
./run.sh
|
|
ls -lh
|
|
popd
|
|
|
|
pushd speech-enhancement-dpdfnet
|
|
echo "speech enhancement with dpdfnet models"
|
|
./run.sh
|
|
ls -lh
|
|
popd
|
|
|
|
pushd streaming-speech-enhancement-gtcrn
|
|
echo "streaming speech enhancement with gtcrn models"
|
|
./run.sh
|
|
ls -lh
|
|
popd
|
|
|
|
pushd streaming-speech-enhancement-dpdfnet
|
|
echo "streaming speech enhancement with dpdfnet models"
|
|
./run.sh
|
|
ls -lh
|
|
popd
|
|
|
|
pushd spoken-language-identification
|
|
./run-whisper.sh
|
|
popd
|
|
|
|
pushd streaming-asr
|
|
|
|
echo '----------streaming T-one ctc----------'
|
|
./run-t-one-ctc.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------streaming zipformer ctc HLG----------'
|
|
./run-zipformer-ctc-hlg.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------streaming zipformer ctc----------'
|
|
./run-zipformer-ctc.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------streaming zipformer transducer----------'
|
|
./run-zipformer-transducer-itn.sh
|
|
./run-zipformer-transducer.sh
|
|
rm -f itn*
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------streaming NeMo transducer----------'
|
|
./run-nemo-transducer.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------streaming paraformer----------'
|
|
./run-paraformer.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
popd # streaming-asr
|
|
|
|
pushd vad
|
|
./run-ten-vad.sh
|
|
./run.sh
|
|
rm *.onnx
|
|
popd
|
|
|
|
pushd speaker-diarization
|
|
echo '----------speaker diarization----------'
|
|
./run.sh
|
|
popd
|
|
|
|
pushd speaker-identification
|
|
echo '----------3d speaker----------'
|
|
./run-3d-speaker.sh
|
|
popd
|
|
|
|
pushd add-punctuations
|
|
echo '----------CT Transformer----------'
|
|
./run-ct-transformer.sh
|
|
echo '----------Online punctuation----------'
|
|
./run-online.sh
|
|
rm -rf sherpa-onnx-online-punct-en-2024-08-06
|
|
popd
|
|
|
|
pushd audio-tagging
|
|
echo '----------zipformer----------'
|
|
./run-zipformer.sh
|
|
|
|
echo '----------ced----------'
|
|
./run-ced.sh
|
|
popd
|
|
|
|
pushd vad-with-non-streaming-asr
|
|
|
|
echo '----------Zipformer CTC----------'
|
|
./run-zipformer-ctc.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------Dolphin CTC----------'
|
|
./run-dolphin-ctc.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo '----------TeleSpeech CTC----------'
|
|
./run-telespeech-ctc.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo "----zipformer transducer----"
|
|
./run-zipformer-transducer.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo "----moonshine----"
|
|
./run-moonshine.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo "----whisper----"
|
|
./run-whisper.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo "----paraformer----"
|
|
./run-paraformer.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo "----SenseVoice zh----"
|
|
./run-sense-voice-zh-2.sh
|
|
./run-sense-voice-zh.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
echo "----SenseVoice en----"
|
|
./run-sense-voice-en.sh
|
|
rm -rf sherpa-onnx-*
|
|
|
|
popd
|
|
|
|
pushd keyword-spotter
|
|
./run-zh.sh
|
|
popd
|