From c2dee5e3c29eba79e591d9e9caebaef15ea4e56b Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期四, 29 六月 2023 11:09:28 +0800
Subject: [PATCH] Merge pull request #687 from alibaba-damo-academy/dev_lhn

---
 funasr/runtime/onnxruntime/src/audio.cpp |  116 ++++++++++++++++++++++++++++++++++++++++++++++++++++++---
 1 files changed, 109 insertions(+), 7 deletions(-)

diff --git a/funasr/runtime/onnxruntime/src/audio.cpp b/funasr/runtime/onnxruntime/src/audio.cpp
index 8f46a4f..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);
     }
 }
 
@@ -237,6 +238,24 @@
         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.
@@ -277,8 +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);
@@ -422,6 +480,33 @@
 
 }
 
+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)
 {
     if (offset >= speech_align_len) {
@@ -496,7 +581,7 @@
     delete frame;
 }
 
-void Audio::Split(Model* recog_obj)
+void Audio::Split(OfflineStream* offline_stream)
 {
     AudioFrame *frame;
 
@@ -507,7 +592,7 @@
     frame = NULL;
 
     std::vector<float> pcm_data(speech_data, speech_data+sp_len);
-    vector<std::vector<int>> vad_segments = recog_obj->VadSeg(pcm_data);
+    vector<std::vector<int>> vad_segments = (offline_stream->vad_handle)->Infer(pcm_data);
     int seg_sample = MODEL_SAMPLE_RATE/1000;
     for(vector<int> segment:vad_segments)
     {
@@ -519,4 +604,21 @@
         frame_queue.push(frame);
         frame = NULL;
     }
-}
\ No newline at end of file
+}
+
+
+void Audio::Split(VadModel* vad_obj, vector<std::vector<int>>& vad_segments, bool input_finished)
+{
+    AudioFrame *frame;
+
+    frame = frame_queue.front();
+    frame_queue.pop();
+    int sp_len = frame->GetLen();
+    delete frame;
+    frame = NULL;
+
+    std::vector<float> pcm_data(speech_data, speech_data+sp_len);
+    vad_segments = vad_obj->Infer(pcm_data, input_finished);
+}
+
+} // namespace funasr
\ No newline at end of file

--
Gitblit v1.9.1