From ac786054dedc55e0b687f686aa6c24fa96bdb9b8 Mon Sep 17 00:00:00 2001
From: yhliang <68215459+yhliang-aslp@users.noreply.github.com>
Date: 星期四, 18 五月 2023 11:02:02 +0800
Subject: [PATCH] Merge pull request #524 from alibaba-damo-academy/main

---
 funasr/runtime/onnxruntime/readme.md                       |   13 +++
 funasr/runtime/onnxruntime/src/funasr-onnx-offline-rtf.cpp |   22 ++++-
 funasr/runtime/html5/static/wsconnecter.js                 |    2 
 funasr/runtime/onnxruntime/src/paraformer.cpp              |    6 +
 funasr/runtime/html5/readme_cn.md                          |    4 
 funasr/runtime/python/websocket/ws_server_online.py        |   65 ++++++++++++----
 funasr/runtime/onnxruntime/src/fsmn-vad.cpp                |   18 ++-
 funasr/runtime/python/benchmark_onnx_cpp.md                |   96 +++++++++++++++++------
 funasr/runtime/onnxruntime/include/vad-model.h             |    8 -
 funasr/runtime/onnxruntime/src/fsmn-vad.h                  |    4 
 10 files changed, 173 insertions(+), 65 deletions(-)

diff --git a/funasr/runtime/html5/readme_cn.md b/funasr/runtime/html5/readme_cn.md
index 612dc20..d1a56eb 100644
--- a/funasr/runtime/html5/readme_cn.md
+++ b/funasr/runtime/html5/readme_cn.md
@@ -103,7 +103,9 @@
     }
   }
 ```
-
+### 淇敼wsconnecter.js閲宎sr鎺ュ彛鍦板潃
+wsconnecter.js閲岄厤缃畂nline asr鏈嶅姟鍦板潃璺緞锛岃繖閲岄厤缃殑鏄痺ss绔彛
+var Uri = "wss://xxx:xxx/wss/" 
 ## Acknowledge
 1. This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR).
 2. We acknowledge [AiHealthx](http://www.aihealthx.com/) for contributing the html5 demo.
\ No newline at end of file
diff --git a/funasr/runtime/html5/static/wsconnecter.js b/funasr/runtime/html5/static/wsconnecter.js
index 4b22e8f..594652d 100644
--- a/funasr/runtime/html5/static/wsconnecter.js
+++ b/funasr/runtime/html5/static/wsconnecter.js
@@ -5,7 +5,7 @@
 /* 2021-2023 by zhaoming,mali aihealthx.com */
 
 function WebSocketConnectMethod( config ) { //瀹氫箟socket杩炴帴鏂规硶绫�
-	var Uri = "wss://111.205.137.58:5821/wss/" //璁剧疆wss asr online鎺ュ彛鍦板潃 濡� wss://X.X.X.X:port/wss/
+    var Uri = "wss://30.220.136.139:5921/"  //	var Uri = "wss://30.221.177.46:5921/" //璁剧疆wss asr online鎺ュ彛鍦板潃 濡� wss://X.X.X.X:port/wss/
 	var speechSokt;
 	var connKeeperID;
 	
diff --git a/funasr/runtime/onnxruntime/include/vad-model.h b/funasr/runtime/onnxruntime/include/vad-model.h
index e37bd97..b1b1e9d 100644
--- a/funasr/runtime/onnxruntime/include/vad-model.h
+++ b/funasr/runtime/onnxruntime/include/vad-model.h
@@ -11,15 +11,11 @@
   public:
     virtual ~VadModel(){};
     virtual void InitVad(const std::string &vad_model, const std::string &vad_cmvn, const std::string &vad_config, int thread_num)=0;
-    virtual std::vector<std::vector<int>> Infer(const std::vector<float> &waves)=0;
+    virtual std::vector<std::vector<int>> Infer(std::vector<float> &waves, bool input_finished=true)=0;
     virtual void ReadModel(const char* vad_model)=0;
     virtual void LoadConfigFromYaml(const char* filename)=0;
     virtual void FbankKaldi(float sample_rate, std::vector<std::vector<float>> &vad_feats,
-                    const std::vector<float> &waves)=0;
-    virtual void LfrCmvn(std::vector<std::vector<float>> &vad_feats)=0;
-    virtual void Forward(
-            const std::vector<std::vector<float>> &chunk_feats,
-            std::vector<std::vector<float>> *out_prob)=0;
+                    std::vector<float> &waves)=0;
     virtual void LoadCmvn(const char *filename)=0;
     virtual void InitCache()=0;
 };
diff --git a/funasr/runtime/onnxruntime/readme.md b/funasr/runtime/onnxruntime/readme.md
index 3e34a67..4ed184f 100644
--- a/funasr/runtime/onnxruntime/readme.md
+++ b/funasr/runtime/onnxruntime/readme.md
@@ -127,6 +127,8 @@
 ### funasr-onnx-offline-rtf
 ```shell
 ./funasr-onnx-offline-rtf     --model-dir <string> [--quantize <string>]
+                              [--vad-dir <string>] [--vad-quant <string>]
+                              [--punc-dir <string>] [--punc-quant <string>]
                               --wav-path <string> --thread-num <int32_t>
                               [--] [--version] [-h]
 Where:
@@ -136,6 +138,17 @@
      (required)  the model path, which contains model.onnx, config.yaml, am.mvn
    --quantize <string>
      false (Default), load the model of model.onnx in model_dir. If set true, load the model of model_quant.onnx in model_dir
+
+   --vad-dir <string>
+     the vad model path, which contains model.onnx, vad.yaml, vad.mvn
+   --vad-quant <string>
+     false (Default), load the model of model.onnx in vad_dir. If set true, load the model of model_quant.onnx in vad_dir
+
+   --punc-dir <string>
+     the punc model path, which contains model.onnx, punc.yaml
+   --punc-quant <string>
+     false (Default), load the model of model.onnx in punc_dir. If set true, load the model of model_quant.onnx in punc_dir
+     
    --wav-path <string>
      (required)  the input could be: 
       wav_path, e.g.: asr_example.wav;
diff --git a/funasr/runtime/onnxruntime/src/fsmn-vad.cpp b/funasr/runtime/onnxruntime/src/fsmn-vad.cpp
index f061534..516dc88 100644
--- a/funasr/runtime/onnxruntime/src/fsmn-vad.cpp
+++ b/funasr/runtime/onnxruntime/src/fsmn-vad.cpp
@@ -162,17 +162,21 @@
     }
   
     // get 4 caches outputs,each size is 128*19
-    for (int i = 1; i < 5; i++) {
-      float* data = vad_ort_outputs[i].GetTensorMutableData<float>();
-      memcpy(in_cache_[i-1].data(), data, sizeof(float) * 128*19);
-    }
+    // for (int i = 1; i < 5; i++) {
+    //   float* data = vad_ort_outputs[i].GetTensorMutableData<float>();
+    //   memcpy(in_cache_[i-1].data(), data, sizeof(float) * 128*19);
+    // }
 }
 
 void FsmnVad::FbankKaldi(float sample_rate, std::vector<std::vector<float>> &vad_feats,
-                         const std::vector<float> &waves) {
+                         std::vector<float> &waves) {
     knf::OnlineFbank fbank(fbank_opts);
 
-    fbank.AcceptWaveform(sample_rate, &waves[0], waves.size());
+    std::vector<float> buf(waves.size());
+    for (int32_t i = 0; i != waves.size(); ++i) {
+        buf[i] = waves[i] * 32768;
+    }
+    fbank.AcceptWaveform(sample_rate, buf.data(), buf.size());
     int32_t frames = fbank.NumFramesReady();
     for (int32_t i = 0; i != frames; ++i) {
         const float *frame = fbank.GetFrame(i);
@@ -267,7 +271,7 @@
 }
 
 std::vector<std::vector<int>>
-FsmnVad::Infer(const std::vector<float> &waves) {
+FsmnVad::Infer(std::vector<float> &waves, bool input_finished) {
     std::vector<std::vector<float>> vad_feats;
     std::vector<std::vector<float>> vad_probs;
     FbankKaldi(vad_sample_rate_, vad_feats, waves);
diff --git a/funasr/runtime/onnxruntime/src/fsmn-vad.h b/funasr/runtime/onnxruntime/src/fsmn-vad.h
index 3d183f8..a8ec4ce 100644
--- a/funasr/runtime/onnxruntime/src/fsmn-vad.h
+++ b/funasr/runtime/onnxruntime/src/fsmn-vad.h
@@ -21,7 +21,7 @@
     ~FsmnVad();
     void Test();
     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);
+    std::vector<std::vector<int>> Infer(std::vector<float> &waves, bool input_finished=true);
     void Reset();
 
 private:
@@ -34,7 +34,7 @@
             std::vector<const char *> *in_names, std::vector<const char *> *out_names);
 
     void FbankKaldi(float sample_rate, std::vector<std::vector<float>> &vad_feats,
-                    const std::vector<float> &waves);
+                    std::vector<float> &waves);
 
     void LfrCmvn(std::vector<std::vector<float>> &vad_feats);
 
diff --git a/funasr/runtime/onnxruntime/src/funasr-onnx-offline-rtf.cpp b/funasr/runtime/onnxruntime/src/funasr-onnx-offline-rtf.cpp
index 6ba65c6..2d182e0 100644
--- a/funasr/runtime/onnxruntime/src/funasr-onnx-offline-rtf.cpp
+++ b/funasr/runtime/onnxruntime/src/funasr-onnx-offline-rtf.cpp
@@ -39,7 +39,7 @@
     // warm up
     for (size_t i = 0; i < 1; i++)
     {
-        FUNASR_RESULT result=FunASRInfer(asr_handle, wav_list[0].c_str(), RASR_NONE, NULL, 16000);
+        FUNASR_RESULT result=FunOfflineInfer(asr_handle, wav_list[0].c_str(), RASR_NONE, NULL, 16000);
     }
 
     while (true) {
@@ -50,7 +50,7 @@
         }
 
         gettimeofday(&start, NULL);
-        FUNASR_RESULT result=FunASRInfer(asr_handle, wav_list[i].c_str(), RASR_NONE, NULL, 16000);
+        FUNASR_RESULT result=FunOfflineInfer(asr_handle, wav_list[i].c_str(), RASR_NONE, NULL, 16000);
 
         gettimeofday(&end, NULL);
         seconds = (end.tv_sec - start.tv_sec);
@@ -102,12 +102,20 @@
     TCLAP::CmdLine cmd("funasr-onnx-offline-rtf", ' ', "1.0");
     TCLAP::ValueArg<std::string>    model_dir("", MODEL_DIR, "the model path, which contains model.onnx, config.yaml, am.mvn", true, "", "string");
     TCLAP::ValueArg<std::string>    quantize("", QUANTIZE, "false (Default), load the model of model.onnx in model_dir. If set true, load the model of model_quant.onnx in model_dir", false, "false", "string");
+    TCLAP::ValueArg<std::string>    vad_dir("", VAD_DIR, "the vad model path, which contains model.onnx, vad.yaml, vad.mvn", false, "", "string");
+    TCLAP::ValueArg<std::string>    vad_quant("", VAD_QUANT, "false (Default), load the model of model.onnx in vad_dir. If set true, load the model of model_quant.onnx in vad_dir", false, "false", "string");
+    TCLAP::ValueArg<std::string>    punc_dir("", PUNC_DIR, "the punc model path, which contains model.onnx, punc.yaml", false, "", "string");
+    TCLAP::ValueArg<std::string>    punc_quant("", PUNC_QUANT, "false (Default), load the model of model.onnx in punc_dir. If set true, load the model of model_quant.onnx in punc_dir", false, "false", "string");
 
     TCLAP::ValueArg<std::string> wav_path("", WAV_PATH, "the input could be: wav_path, e.g.: asr_example.wav; pcm_path, e.g.: asr_example.pcm; wav.scp, kaldi style wav list (wav_id \t wav_path)", true, "", "string");
     TCLAP::ValueArg<std::int32_t> thread_num("", THREAD_NUM, "multi-thread num for rtf", true, 0, "int32_t");
 
     cmd.add(model_dir);
     cmd.add(quantize);
+    cmd.add(vad_dir);
+    cmd.add(vad_quant);
+    cmd.add(punc_dir);
+    cmd.add(punc_quant);
     cmd.add(wav_path);
     cmd.add(thread_num);
     cmd.parse(argc, argv);
@@ -115,11 +123,15 @@
     std::map<std::string, std::string> model_path;
     GetValue(model_dir, MODEL_DIR, model_path);
     GetValue(quantize, QUANTIZE, model_path);
+    GetValue(vad_dir, VAD_DIR, model_path);
+    GetValue(vad_quant, VAD_QUANT, model_path);
+    GetValue(punc_dir, PUNC_DIR, model_path);
+    GetValue(punc_quant, PUNC_QUANT, model_path);
     GetValue(wav_path, WAV_PATH, model_path);
 
     struct timeval start, end;
     gettimeofday(&start, NULL);
-    FUNASR_HANDLE asr_handle=FunASRInit(model_path, 1);
+    FUNASR_HANDLE asr_handle=FunOfflineInit(model_path, 1);
 
     if (!asr_handle)
     {
@@ -132,7 +144,7 @@
     long modle_init_micros = ((seconds * 1000000) + end.tv_usec) - (start.tv_usec);
     LOG(INFO) << "Model initialization takes " << (double)modle_init_micros / 1000000 << " s";
 
-    // read wav_scp
+    // read wav_path
     vector<string> wav_list;
     string wav_path_ = model_path.at(WAV_PATH);
     if(is_target_file(wav_path_, "wav") || is_target_file(wav_path_, "pcm")){
@@ -179,6 +191,6 @@
     LOG(INFO) << "total_rtf " << (double)total_time/ (total_length*1000000);
     LOG(INFO) << "speedup " << 1.0/((double)total_time/ (total_length*1000000));
 
-    FunASRUninit(asr_handle);
+    FunOfflineUninit(asr_handle);
     return 0;
 }
diff --git a/funasr/runtime/onnxruntime/src/paraformer.cpp b/funasr/runtime/onnxruntime/src/paraformer.cpp
index 74366a0..1957a12 100644
--- a/funasr/runtime/onnxruntime/src/paraformer.cpp
+++ b/funasr/runtime/onnxruntime/src/paraformer.cpp
@@ -69,7 +69,11 @@
 
 vector<float> Paraformer::FbankKaldi(float sample_rate, const float* waves, int len) {
     knf::OnlineFbank fbank_(fbank_opts);
-    fbank_.AcceptWaveform(sample_rate, waves, len);
+    std::vector<float> buf(len);
+    for (int32_t i = 0; i != len; ++i) {
+        buf[i] = waves[i] * 32768;
+    }
+    fbank_.AcceptWaveform(sample_rate, buf.data(), buf.size());
     //fbank_->InputFinished();
     int32_t frames = fbank_.NumFramesReady();
     int32_t feature_dim = fbank_opts.mel_opts.num_bins;
diff --git a/funasr/runtime/python/benchmark_onnx_cpp.md b/funasr/runtime/python/benchmark_onnx_cpp.md
index d71fae3..0ba7ff2 100644
--- a/funasr/runtime/python/benchmark_onnx_cpp.md
+++ b/funasr/runtime/python/benchmark_onnx_cpp.md
@@ -43,20 +43,16 @@
 make
 ```
 
-#### Recipe
-
-set the model, data path and output_dir
-
-```shell
-./bin/funasr-onnx-offline-rtf /path/to/model_dir /path/to/wav.scp quantize(true or false) thread_num
-```
-
-The structure of /path/to/models_dir
-```
-config.yaml, am.mvn, model.onnx(or model_quant.onnx)
-```
-
 ## [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) 
+```shell
+./funasr-onnx-offline-rtf \
+    --model-dir    ./asrmodel/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch \
+    --quantize  true \
+    --wav-path     ./aishell1_test.scp  \
+    --thread-num 32
+
+Node: '--quantize false' means fp32, otherwise it will be int8 
+```
 
 Number of Parameter: 220M 
 
@@ -90,18 +86,66 @@
 ### Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz    32core-64processor   without avx512_vnni
 
 | concurrent-tasks    | processing time(s) | RTF      | Speedup Rate |
-|---------------------|--------------------|----------|--------------|
-|  1   (onnx fp32)    | 2903s              | 0.080404 | 12           |
-|  1   (onnx int8)    | 2714s              | 0.075168 | 13           |
-|  8   (onnx fp32)    | 373s               | 0.010329 | 97           |
-|  8   (onnx int8)    | 340s               | 0.009428 | 106          |
-|  16   (onnx fp32)   | 189s               | 0.005252 | 190          |
-|  16   (onnx int8)   | 174s               | 0.004817 | 207          |
-|  32   (onnx fp32)   | 109s               | 0.00301  | 332          |
-|  32   (onnx int8)   | 88s                | 0.00245  | 408          |
-|  64   (onnx fp32)   | 113s               | 0.003129 | 320          |
-|  64   (onnx int8)   | 79s                | 0.002201 | 454          |
-|  96   (onnx fp32)   | 115s               | 0.003183 | 314          |
-|  96   (onnx int8)   | 80s                | 0.002222 | 450          |
+|---------------------|:------------------:|----------|:------------:|
+|  1   (onnx fp32)    |       2903s        | 0.080404 |      12      |
+|  1   (onnx int8)    |       2714s        | 0.075168 |      13      |
+|  8   (onnx fp32)    |        373s        | 0.010329 |      97      |
+|  8   (onnx int8)    |        340s        | 0.009428 |     106      |
+|  16   (onnx fp32)   |        189s        | 0.005252 |     190      |
+|  16   (onnx int8)   |        174s        | 0.004817 |     207      |
+|  32   (onnx fp32)   |        109s        | 0.00301  |     332      |
+|  32   (onnx int8)   |        88s         | 0.00245  |     408      |
+|  64   (onnx fp32)   |        113s        | 0.003129 |     320      |
+|  64   (onnx int8)   |        79s         | 0.002201 |     454      |
+|  96   (onnx fp32)   |        115s        | 0.003183 |     314      |
+|  96   (onnx int8)   |        80s         | 0.002222 |     450      |
+
+## [FSMN-VAD](https://www.modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) + [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) + [CT-Transformer](https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/summary)
+
+```shell
+./funasr-onnx-offline-rtf \
+    --model-dir    ./asrmodel/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch \
+    --quantize  true \
+    --vad-dir   ./asrmodel/speech_fsmn_vad_zh-cn-16k-common-pytorch \
+    --punc-dir  ./asrmodel/punc_ct-transformer_zh-cn-common-vocab272727-pytorch \
+    --wav-path     ./aishell1_test.scp  \
+    --thread-num 32
+
+Node: '--quantize false' means fp32, otherwise it will be int8 
+```
+
+ ### Intel(R) Xeon(R) Platinum 8369B CPU @ 2.90GHz   16core-32processor    with avx512_vnni
+
+| concurrent-tasks    | processing time(s) |   RTF    | Speedup Rate |
+|---------------------|:------------------:|:--------:|:------------:|
+|  1   (onnx fp32)    |       2134s        |  0.0591  |      17      |
+|  1   (onnx int8)    |       1047s        |  0.029   |      34      |
+|  8   (onnx fp32)    |        273s        | 0.007557 |     132      |
+|  8   (onnx int8)    |        132s        | 0.003647 |     274      |
+|  16   (onnx fp32)   |        147s        | 0.004061 |     246      |
+|  16   (onnx int8)   |        69s         | 0.001916 |     521      |
+|  32   (onnx fp32)   |        133s        | 0.003675 |     272      |
+|  32   (onnx int8)   |        65s         | 0.001786 |     559      |
+|  64   (onnx fp32)   |        136s        | 0.003767 |     265      |
+|  64   (onnx int8)   |        67s         | 0.001867 |     535      |
+|  96   (onnx fp32)   |        137s        | 0.003802 |     262      |
+|  96   (onnx int8)   |        69s         | 0.001904 |     524      |
 
 
+
+### Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz    32core-64processor   without avx512_vnni
+
+| concurrent-tasks    | processing time(s) | RTF      | Speedup Rate |
+|---------------------|:------------------:|----------|:------------:|
+|  1   (onnx fp32)    |       3073s        | 0.0851   |      12      |
+|  1   (onnx int8)    |       2840s        | 0.0787   |      13      |
+|  8   (onnx fp32)    |        389s        | 0.01079  |      93      |
+|  8   (onnx int8)    |        355s        | 0.0098   |     101      |
+|  16   (onnx fp32)   |        199s        | 0.005513 |     181      |
+|  16   (onnx int8)   |        171s        | 0.004784 |     210      |
+|  32   (onnx fp32)   |        113s        | 0.00314  |     318      |
+|  32   (onnx int8)   |        92s         | 0.00255  |     391      |
+|  64   (onnx fp32)   |        115s        | 0.0032   |     312      |
+|  64   (onnx int8)   |        81s         | 0.002232 |     448      |
+|  96   (onnx fp32)   |        117s        | 0.003257 |     307      |
+|  96   (onnx int8)   |        81s         | 0.002258 |     442      |
diff --git a/funasr/runtime/python/websocket/ws_server_online.py b/funasr/runtime/python/websocket/ws_server_online.py
index 16a3abe..2255688 100644
--- a/funasr/runtime/python/websocket/ws_server_online.py
+++ b/funasr/runtime/python/websocket/ws_server_online.py
@@ -32,15 +32,29 @@
 	ncpu=args.ncpu,
 	model_revision='v1.0.4')
 
+# vad
+inference_pipeline_vad = pipeline(
+    task=Tasks.voice_activity_detection,
+    model=args.vad_model,
+    model_revision=None,
+    output_dir=None,
+    batch_size=1,
+    mode='online',
+    ngpu=args.ngpu,
+    ncpu=1,
+)
+
 print("model loaded")
 
 
 
 async def ws_serve(websocket, path):
+	frames = []
 	frames_asr_online = []
 	global websocket_users
 	websocket_users.add(websocket)
 	websocket.param_dict_asr_online = {"cache": dict()}
+	websocket.param_dict_vad = {'in_cache': dict()}
 	websocket.wav_name = "microphone"
 	print("new user connected",flush=True)
 	try:
@@ -53,9 +67,10 @@
 				if "is_speaking" in messagejson:
 					websocket.is_speaking = messagejson["is_speaking"]
 					websocket.param_dict_asr_online["is_final"] = not websocket.is_speaking
+					websocket.param_dict_vad["is_final"] = not websocket.is_speaking
 					# need to fire engine manually if no data received any more
 					if not websocket.is_speaking:
-						await async_asr_online(websocket,b"")
+						await async_asr_online(websocket, b"")
 				if "chunk_interval" in messagejson:
 					websocket.chunk_interval=messagejson["chunk_interval"]
 				if "wav_name" in messagejson:
@@ -64,14 +79,18 @@
 					websocket.param_dict_asr_online["chunk_size"] = messagejson["chunk_size"]
 			# if has bytes in buffer or message is bytes
 			if len(frames_asr_online) > 0 or not isinstance(message, str):
-				if not isinstance(message,str):
+				if not isinstance(message, str):
 					frames_asr_online.append(message)
+					# frames.append(message)
+					# duration_ms = len(message) // 32
+					# websocket.vad_pre_idx += duration_ms
+					speech_start_i, speech_end_i = await async_vad(websocket, message)
+					websocket.is_speaking = not speech_end_i
+					
 				if len(frames_asr_online) % websocket.chunk_interval == 0 or not websocket.is_speaking:
+					websocket.param_dict_asr_online["is_final"] = not websocket.is_speaking
 					audio_in = b"".join(frames_asr_online)
-					# if not websocket.is_speaking:
-						#padding 0.5s at end gurantee that asr engine can fire out last word
-						# audio_in=audio_in+b''.join(np.zeros(int(16000*0.5),dtype=np.int16))
-					await async_asr_online(websocket,audio_in)
+					await async_asr_online(websocket, audio_in)
 					frames_asr_online = []
 	
 	
@@ -85,7 +104,7 @@
 
 
 async def async_asr_online(websocket,audio_in):
-	if len(audio_in) >=0:
+	if len(audio_in) >= 0:
 		audio_in = load_bytes(audio_in)
 		rec_result = inference_pipeline_asr_online(audio_in=audio_in,
 		                                           param_dict=websocket.param_dict_asr_online)
@@ -97,16 +116,30 @@
 				await websocket.send(message)
 
 
+async def async_vad(websocket, audio_in):
+	segments_result = inference_pipeline_vad(audio_in=audio_in, param_dict=websocket.param_dict_vad)
+	
+	speech_start = False
+	speech_end = False
+	
+	if len(segments_result) == 0 or len(segments_result["text"]) > 1:
+		return speech_start, speech_end
+	if segments_result["text"][0][0] != -1:
+		speech_start = segments_result["text"][0][0]
+	if segments_result["text"][0][1] != -1:
+		speech_end = True
+	return speech_start, speech_end
+
 if len(args.certfile)>0:
-  ssl_context = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
-
-  # Generate with Lets Encrypt, copied to this location, chown to current user and 400 permissions
-  ssl_cert = args.certfile
-  ssl_key = args.keyfile
-
-  ssl_context.load_cert_chain(ssl_cert, keyfile=ssl_key)
-  start_server = websockets.serve(ws_serve, args.host, args.port, subprotocols=["binary"], ping_interval=None,ssl=ssl_context)
+	ssl_context = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
+	
+	# Generate with Lets Encrypt, copied to this location, chown to current user and 400 permissions
+	ssl_cert = args.certfile
+	ssl_key = args.keyfile
+	
+	ssl_context.load_cert_chain(ssl_cert, keyfile=ssl_key)
+	start_server = websockets.serve(ws_serve, args.host, args.port, subprotocols=["binary"], ping_interval=None,ssl=ssl_context)
 else:
-  start_server = websockets.serve(ws_serve, args.host, args.port, subprotocols=["binary"], ping_interval=None)
+	start_server = websockets.serve(ws_serve, args.host, args.port, subprotocols=["binary"], ping_interval=None)
 asyncio.get_event_loop().run_until_complete(start_server)
 asyncio.get_event_loop().run_forever()
\ No newline at end of file

--
Gitblit v1.9.1