From 4ee715e70e36cdba7b05fe044fecab9cf4fa16ff Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 03 七月 2023 17:23:02 +0800
Subject: [PATCH] websocket bug
---
funasr/runtime/onnxruntime/src/audio.cpp | 94 +++++++++++++++++++++++++++++++++++++++++++---
1 files changed, 87 insertions(+), 7 deletions(-)
diff --git a/funasr/runtime/onnxruntime/src/audio.cpp b/funasr/runtime/onnxruntime/src/audio.cpp
index 6113614..23d0010 100644
--- a/funasr/runtime/onnxruntime/src/audio.cpp
+++ b/funasr/runtime/onnxruntime/src/audio.cpp
@@ -11,6 +11,7 @@
using namespace std;
+namespace funasr {
// see http://soundfile.sapp.org/doc/WaveFormat/
// Note: We assume little endian here
struct WaveHeader {
@@ -175,12 +176,12 @@
{
if (speech_buff != NULL) {
free(speech_buff);
-
}
-
if (speech_data != NULL) {
-
free(speech_data);
+ }
+ if (speech_char != NULL) {
+ free(speech_char);
}
}
@@ -247,6 +248,15 @@
return false;
}
+ if (!header.Validate()) {
+ return false;
+ }
+
+ header.SeekToDataChunk(is);
+ if (!is) {
+ return false;
+ }
+
*sampling_rate = header.sample_rate;
// header.subchunk2_size contains the number of bytes in the data.
// As we assume each sample contains two bytes, so it is divided by 2 here
@@ -286,8 +296,47 @@
return false;
}
-bool Audio::LoadWav(const char* buf, int n_file_len, int32_t* sampling_rate)
+bool Audio::LoadWav2Char(const char *filename, int32_t* sampling_rate)
{
+ WaveHeader header;
+ if (speech_char != NULL) {
+ free(speech_char);
+ }
+ offset = 0;
+ std::ifstream is(filename, std::ifstream::binary);
+ is.read(reinterpret_cast<char *>(&header), sizeof(header));
+ if(!is){
+ LOG(ERROR) << "Failed to read " << filename;
+ return false;
+ }
+ if (!header.Validate()) {
+ return false;
+ }
+ header.SeekToDataChunk(is);
+ if (!is) {
+ return false;
+ }
+ if (!header.Validate()) {
+ return false;
+ }
+ header.SeekToDataChunk(is);
+ if (!is) {
+ return false;
+ }
+
+ *sampling_rate = header.sample_rate;
+ // header.subchunk2_size contains the number of bytes in the data.
+ // As we assume each sample contains two bytes, so it is divided by 2 here
+ speech_len = header.subchunk2_size / 2;
+ speech_char = (char *)malloc(header.subchunk2_size);
+ memset(speech_char, 0, header.subchunk2_size);
+ is.read(speech_char, header.subchunk2_size);
+
+ return true;
+}
+
+bool Audio::LoadWav(const char* buf, int n_file_len, int32_t* sampling_rate)
+{
WaveHeader header;
if (speech_data != NULL) {
free(speech_data);
@@ -389,8 +438,10 @@
FILE* fp;
fp = fopen(filename, "rb");
if (fp == nullptr)
+ {
LOG(ERROR) << "Failed to read " << filename;
return false;
+ }
fseek(fp, 0, SEEK_END);
uint32_t n_file_len = ftell(fp);
fseek(fp, 0, SEEK_SET);
@@ -427,6 +478,33 @@
else
return false;
+}
+
+bool Audio::LoadPcmwav2Char(const char* filename, int32_t* sampling_rate)
+{
+ if (speech_char != NULL) {
+ free(speech_char);
+ }
+ offset = 0;
+
+ FILE* fp;
+ fp = fopen(filename, "rb");
+ if (fp == nullptr)
+ {
+ LOG(ERROR) << "Failed to read " << filename;
+ return false;
+ }
+ fseek(fp, 0, SEEK_END);
+ uint32_t n_file_len = ftell(fp);
+ fseek(fp, 0, SEEK_SET);
+
+ speech_len = (n_file_len) / 2;
+ speech_char = (char *)malloc(n_file_len);
+ memset(speech_char, 0, n_file_len);
+ fread(speech_char, sizeof(int16_t), n_file_len/2, fp);
+ fclose(fp);
+
+ return true;
}
int Audio::FetchChunck(float *&dout, int len)
@@ -529,7 +607,7 @@
}
-void Audio::Split(VadModel* vad_obj, vector<std::vector<int>>& vad_segments)
+void Audio::Split(VadModel* vad_obj, vector<std::vector<int>>& vad_segments, bool input_finished)
{
AudioFrame *frame;
@@ -540,5 +618,7 @@
frame = NULL;
std::vector<float> pcm_data(speech_data, speech_data+sp_len);
- vad_segments = vad_obj->Infer(pcm_data);
-}
\ No newline at end of file
+ vad_segments = vad_obj->Infer(pcm_data, input_finished);
+}
+
+} // namespace funasr
\ No newline at end of file
--
Gitblit v1.9.1