update the acs server config, test=doc

demos/audio_content_search/README.md

@@ -2,9 +2,9 @@
 # ACS (Audio Content Search)
 
 ## Introduction
-ACS, or Audio Content Search, refers to the problem of getting the key word time stamp to from automatically transcribe spoken language (speech-to-text). 
+ACS, or Audio Content Search, refers to the problem of getting the key word time stamp from automatically transcribe spoken language (speech-to-text). 
 
-This demo is an implementation to get the key word stamp from the text from a specific audio file. It can be done by a single command or a few lines in python using `PaddleSpeech`. 
+This demo is an implementation of obtaining the keyword timestamp in the text from a given audio file. It can be done by a single command or a few lines in python using `PaddleSpeech`. 
 
 ## Usage
 ### 1. Installation
@@ -12,6 +12,7 @@ see [installation](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/doc
 
 You can choose one way from meduim and hard to install paddlespeech.
 
+The dependency refers to the requirements.txt
 ### 2. Prepare Input File
 The input of this demo should be a WAV file(`.wav`), and the sample rate must be the same as the model.
 

demos/audio_content_search/README_cn.md

@@ -11,6 +11,7 @@
 请看[安装文档](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install_cn.md)。
 
 你可以从 medium，hard 三中方式中选择一种方式安装。
+依赖参见 requirements.txt
 
 ### 2. 准备输入
 这个 demo 的输入应该是一个 WAV 文件（`.wav`），并且采样率必须与模型的采样率相同。

demos/audio_content_search/conf/acs_application.yaml

@@ -1,5 +1,3 @@
-# This is the parameter configuration file for PaddleSpeech Serving.
-
 #################################################################################
 #                             SERVER SETTING                                    #
 #################################################################################
@@ -18,8 +16,8 @@ engine_list: ['acs_python']
 #                                ENGINE CONFIG                                  #
 #################################################################################
 
-################################### Text #########################################
+################################### ACS #########################################
-################### acs task: engine_type: python #######################
+################### acs task: engine_type: python ###############################
 acs_python:
     task: acs
     asr_protocol: 'websocket' # 'websocket'

demos/audio_content_search/conf/ws_conformer_application.yaml

@@ -1,10 +1,8 @@
-# This is the parameter configuration file for PaddleSpeech Serving.
-
 #################################################################################
 #                             SERVER SETTING                                    #
 #################################################################################
 host: 0.0.0.0
-port: 8090
+port: 8390
 
 # The task format in the engin_list is: <speech task>_<engine type>
 # task choices = ['asr_online']
@@ -27,7 +25,7 @@ asr_online:
     lang: 'zh'
     sample_rate: 16000
     cfg_path: 
-    decode_method: 
+    decode_method: 'attention_rescoring' 
     force_yes: True
     device: 'cpu' # cpu or gpu:id
     am_predictor_conf:

demos/audio_content_search/run.sh

@@ -1,6 +1,7 @@
 export CUDA_VISIBLE_DEVICE=0,1,2,3
-#nohup python3 streaming_asr_server.py --config_file conf/ws_conformer_application.yaml &> streaming_asr.log &
+# we need the streaming asr server
+nohup python3 streaming_asr_server.py --config_file conf/ws_conformer_application.yaml > streaming_asr.log  2>&1  &
 
-# nohup python3 punc_server.py --config_file conf/punc_application.yaml > punc.log 2>&1 &
+# start the acs server
-paddlespeech_server start --config_file conf/acs_application.yaml 
+nohup paddlespeech_server start --config_file conf/acs_application.yaml > acs.log 2>&1 &