EngineX-Iluvatar/enginex-mr_series-sherpa-onnx
Archived
16
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Add C API for speech enhancement GTCRN models (#1984)

Browse Source
This commit is contained in:
Fangjun Kuang
2025-03-11 15:50:04 +08:00
committed by GitHub
parent 5d2d792b1d
commit c5dbf1177c
6 changed files with 238 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
c-api-examples/CMakeLists.txt
View File

@@ -7,6 +7,9 @@ target_link_libraries(decode-file-c-api sherpa-onnx-c-api cargs)
add_executable(kws-c-api kws-c-api.c)
target_link_libraries(kws-c-api sherpa-onnx-c-api)
add_executable(speech-enhancement-gtcrn-c-api speech-enhancement-gtcrn-c-api.c)
target_link_libraries(speech-enhancement-gtcrn-c-api sherpa-onnx-c-api)
if(SHERPA_ONNX_ENABLE_TTS)
add_executable(offline-tts-c-api offline-tts-c-api.c)
target_link_libraries(offline-tts-c-api sherpa-onnx-c-api cargs)

55
c-api-examples/speech-enhancement-gtcrn-c-api.c Normal file
View File

@@ -0,0 +1,55 @@
// c-api-examples/speech-enhancement-gtcrn-c-api.c
//
// Copyright (c) 2025 Xiaomi Corporation
//
// We assume you have pre-downloaded model
// from
// https://github.com/k2-fsa/sherpa-onnx/releases/tag/speech-enhancement-models
//
//
// An example command to download
// clang-format off
/*
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/speech-enhancement-models/gtcrn_simple.onnx
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/speech-enhancement-models/inp_16k.wav
*/
// clang-format on
#include <stdio.h>
#include <string.h>
#include "sherpa-onnx/c-api/c-api.h"
int32_t main() {
SherpaOnnxOfflineSpeechDenoiserConfig config;
const char *wav_filename = "./inp_16k.wav";
const char *out_wave_filename = "./enhanced_16k.wav";
memset(&config, 0, sizeof(config));
config.model.gtcrn.model = "./gtcrn_simple.onnx";
const SherpaOnnxOfflineSpeechDenoiser *sd =
SherpaOnnxCreateOfflineSpeechDenoiser(&config);
if (!sd) {
fprintf(stderr, "Please check your config");
return -1;
}
const SherpaOnnxWave *wave = SherpaOnnxReadWave(wav_filename);
if (wave == NULL) {
SherpaOnnxDestroyOfflineSpeechDenoiser(sd);
fprintf(stderr, "Failed to read %s\n", wav_filename);
return -1;
}
const SherpaOnnxDenoisedAudio *denoised = SherpaOnnxOfflineSpeechDenoiserRun(
sd, wave->samples, wave->num_samples, wave->sample_rate);
SherpaOnnxWriteWave(denoised->samples, denoised->n, denoised->sample_rate,
out_wave_filename);
SherpaOnnxDestroyDenoisedAudio(denoised);
SherpaOnnxFreeWave(wave);
SherpaOnnxDestroyOfflineSpeechDenoiser(sd);
fprintf(stdout, "Saved to %s\n", out_wave_filename);
}