Introduction
This folder contains C# API examples for sherpa-onnx.
Please refer to the documentation https://k2-fsa.github.io/sherpa/onnx/csharp-api/index.html for details.
-
./speech-enhancement-gtcrn It shows how to use the offline speech denoiser API with GTCRN models.
-
./speech-enhancement-dpdfnet It shows how to use the offline speech denoiser API with DPDFNet models. Use 16 kHz DPDFNet models such as
dpdfnet_baseline.onnx,dpdfnet2.onnx,dpdfnet4.onnx, ordpdfnet8.onnxfor downstream ASR anddpdfnet2_48khz_hr.onnxfor 48 kHz enhancement output. -
./streaming-speech-enhancement-gtcrn It shows how to use the online speech denoiser API with GTCRN models.
-
./streaming-speech-enhancement-dpdfnet It shows how to use the online speech denoiser API with DPDFNet models.
-
./speech-enhancement-voxlock It shows how to use the offline speech denoiser API with VoxLock for target-speaker voice isolation.
-
./speech-enhancement-voxlock-with-voice-sample It shows how to use the offline speech denoiser API with VoxLock and a voice sample of the speaker to keep.
-
./streaming-speech-enhancement-voxlock It shows how to use the online speech denoiser API with VoxLock.
-
./streaming-speech-enhancement-voxlock-with-voice-sample It shows how to use the online speech denoiser API with VoxLock and a voice sample of the speaker to keep.
-
./zipvoice-tts-lexicon It shows how to use ZipVoice for Chinese/English zero-shot text-to-speech with the lexicon text frontend.
-
./zipvoice-tts-play-lexicon It shows how to use ZipVoice for Chinese/English zero-shot text-to-speech with playback.
The TTS examples come in two text-frontend flavors:
*-lexicon— a lexicon file, no external phonemizer*-phonemize— the text is phonemized outside of sherpa-onnx with piper-phonemize (see./offline-tts-phonemize,./kitten-tts-phonemize,./kokoro-tts-phonemize)
dotnet new console -n offline-tts-play-lexicon
dotnet sln ./sherpa-onnx.sln add ./offline-tts-play-lexicon
dotnet nuget locals all --list
dotnet nuget locals all --clear