From ddfcd68c803c226f4b2a60b0666b29c24d04c259 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 14 四月 2023 13:15:29 +0800
Subject: [PATCH] Merge pull request #353 from alibaba-damo-academy/dev_lyb
---
funasr/runtime/onnxruntime/include/Audio.h | 17 ++++++++++++-----
1 files changed, 12 insertions(+), 5 deletions(-)
diff --git a/funasr/runtime/onnxruntime/include/Audio.h b/funasr/runtime/onnxruntime/include/Audio.h
index da5e82c..ec49a9f 100644
--- a/funasr/runtime/onnxruntime/include/Audio.h
+++ b/funasr/runtime/onnxruntime/include/Audio.h
@@ -6,6 +6,13 @@
#include <queue>
#include <stdint.h>
+#ifndef model_sample_rate
+#define model_sample_rate 16000
+#endif
+#ifndef WAV_HEADER_SIZE
+#define WAV_HEADER_SIZE 44
+#endif
+
using namespace std;
class AudioFrame {
@@ -32,7 +39,6 @@
int16_t *speech_buff;
int speech_len;
int speech_align_len;
- int16_t sample_rate;
int offset;
float align_size;
int data_type;
@@ -43,10 +49,11 @@
Audio(int data_type, int size);
~Audio();
void disp();
- bool loadwav(const char* filename);
- bool loadwav(const char* buf, int nLen);
- bool loadpcmwav(const char* buf, int nFileLen);
- bool loadpcmwav(const char* filename);
+ bool loadwav(const char* filename, int32_t* sampling_rate);
+ void wavResample(int32_t sampling_rate, const float *waveform, int32_t n);
+ bool loadwav(const char* buf, int nLen, int32_t* sampling_rate);
+ bool loadpcmwav(const char* buf, int nFileLen, int32_t* sampling_rate);
+ bool loadpcmwav(const char* filename, int32_t* sampling_rate);
int fetch_chunck(float *&dout, int len);
int fetch(float *&dout, int &len, int &flag);
void padding();
--
Gitblit v1.9.1