sherpa-onnx/go-api-examples

Introduction

This folder contains Go API examples for sherpa-onnx.

Please refer to the documentation https://k2-fsa.github.io/sherpa/onnx/go-api/index.html for details.

• ./add-punctuation It shows how to use a punctuation model to add punctuations to text

• ./add-punctuation-online It shows how to use an online punctuation model to add punctuations and casing to text

• ./non-streaming-decode-files It shows how to use a non-streaming ASR model to decode files

• ./non-streaming-speaker-diarization It shows how to use a speaker segmentation model and a speaker embedding model for speaker diarization.

• ./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.

• ./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.

• ./speech-enhancement-voxlock-with-voice-sample It shows how to use the offline speech denoiser API with VoxLock and a voice sample.

• ./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.

• ./non-streaming-tts It shows how to use a non-streaming TTS model to convert text to speech. It uses a lexicon file for text normalization.

• ./non-streaming-tts-phonemize It shows how to use a non-streaming TTS model to convert text to speech. It phonemizes the text outside of sherpa-onnx with piper-phonemize-go and passes the phoneme codepoints to sherpa-onnx.

• ./offline-tts-play It shows how to use a non-streaming TTS model to convert text to speech. It plays the audio back as it is being generated.

• ./zero-shot-pocket-tts It shows how to use a PocketTTS model for zero-shot TTS.

• ./zero-shot-pocket-tts-play It shows how to use a PocketTTS model for zero-shot TTS. It plays the audio back as it is being generated.

• ./zero-shot-zipvoice-tts It shows how to use a ZipVoice model for zero-shot TTS with the GenerationConfig API.

• ./zero-shot-zipvoice-tts-play It shows how to use a ZipVoice model for zero-shot TTS. It plays the audio back as it is being generated.

• ./real-time-speech-recognition-from-microphone It shows how to use a streaming ASR model to recognize speech from a microphone in real-time

• ./speaker-identification It shows how to use a speaker embedding model for speaker identification.

• ./streaming-decode-files It shows how to use a streaming model for streaming speech recognition

• ./streaming-hlg-decoding It shows how to use a streaming model for streaming speech recognition with HLG decoding

• ./vad It shows how to use silero VAD with Golang.

• ./vad-asr-paraformer It shows how to use silero VAD + Paraformer for speech recognition.

• ./vad-asr-whisper It shows how to use silero VAD + Whisper

• ./vad-speaker-identification It shows how to use Go API for VAD + speaker identification. for speech recognition.

• ./vad-spoken-language-identification It shows how to use silero VAD + Whisper for spoken language identification.