From 3d9f094e9652d4b84894c6fd4eae39a4a753b0f0 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 16 五月 2023 23:48:00 +0800
Subject: [PATCH] train
---
funasr/runtime/onnxruntime/src/fsmn-vad.h | 26 +++++++++++++++-----------
1 files changed, 15 insertions(+), 11 deletions(-)
diff --git a/funasr/runtime/onnxruntime/src/fsmn-vad.h b/funasr/runtime/onnxruntime/src/fsmn-vad.h
index a27ea0f..3d183f8 100644
--- a/funasr/runtime/onnxruntime/src/fsmn-vad.h
+++ b/funasr/runtime/onnxruntime/src/fsmn-vad.h
@@ -8,7 +8,8 @@
#include "precomp.h"
-class FsmnVad {
+namespace funasr {
+class FsmnVad : public VadModel {
/**
* Author: Speech Lab of DAMO Academy, Alibaba Group
* Deep-FSMN for Large Vocabulary Continuous Speech Recognition
@@ -17,16 +18,16 @@
public:
FsmnVad();
+ ~FsmnVad();
void Test();
- void InitVad(const std::string &vad_model, const std::string &vad_cmvn, int vad_sample_rate, int vad_silence_duration, int vad_max_len,
- float vad_speech_noise_thres);
-
+ void InitVad(const std::string &vad_model, const std::string &vad_cmvn, const std::string &vad_config, int thread_num);
std::vector<std::vector<int>> Infer(const std::vector<float> &waves);
void Reset();
private:
- void ReadModel(const std::string &vad_model);
+ void ReadModel(const char* vad_model);
+ void LoadConfigFromYaml(const char* filename);
static void GetInputOutputInfo(
const std::shared_ptr<Ort::Session> &session,
@@ -35,7 +36,7 @@
void FbankKaldi(float sample_rate, std::vector<std::vector<float>> &vad_feats,
const std::vector<float> &waves);
- std::vector<std::vector<float>> &LfrCmvn(std::vector<std::vector<float>> &vad_feats, int lfr_m, int lfr_n);
+ void LfrCmvn(std::vector<std::vector<float>> &vad_feats);
void Forward(
const std::vector<std::vector<float>> &chunk_feats,
@@ -54,11 +55,14 @@
knf::FbankOptions fbank_opts;
std::vector<float> means_list;
std::vector<float> vars_list;
- int vad_sample_rate_ = 16000;
- int vad_silence_duration_ = 800;
- int vad_max_len_ = 15000;
- double vad_speech_noise_thres_ = 0.9;
+
+ int vad_sample_rate_ = MODEL_SAMPLE_RATE;
+ int vad_silence_duration_ = VAD_SILENCE_DURATION;
+ int vad_max_len_ = VAD_MAX_LEN;
+ double vad_speech_noise_thres_ = VAD_SPEECH_NOISE_THRES;
+ int lfr_m = VAD_LFR_M;
+ int lfr_n = VAD_LFR_N;
};
-
+} // namespace funasr
#endif //VAD_SERVER_FSMNVAD_H
--
Gitblit v1.9.1