|
sherpa-onnx C API 1.0
Public C API and C++ wrapper for sherpa-onnx
|
VoxLock target-speaker voice isolation model configuration. More...
#include <cxx-api.h>
Public Attributes | |
| std::string | enroll_model |
| std::string | chunk_model |
| std::string | voice_sample |
VoxLock keeps the voice of one speaker (the caller) and removes other voices. The model is from https://github.com/arbazsiddiqui/voxlock
| std::string sherpa_onnx::cxx::OfflineSpeechDenoiserVoxLockModelConfig::chunk_model |
| std::string sherpa_onnx::cxx::OfflineSpeechDenoiserVoxLockModelConfig::enroll_model |
| std::string sherpa_onnx::cxx::OfflineSpeechDenoiserVoxLockModelConfig::voice_sample |
Optional. Path to a wave file with at least 3 seconds of the caller's voice. From a longer file, the loudest 3 seconds within the first 30 seconds are used. A file that is shorter or cannot be read is ignored, as if it were empty. If empty or ignored, the voice sample is taken from the input audio; see the C API docs for the offline/online fallbacks.