FunASR离线文件转写服务开发指南-debian-10.13

FunASR离线文件转写服务开发指南-debian-10.13

服务器环境

debian10.13 64位

第一步 配置静态网卡

auto eth0
iface eth0 inet static
address 192.168.1.100
netmask 255.255.255.0
gateway 192.168.1.1
dns-nameservers 8.8.8.8 8.8.4.4

/etc/init.d/networking restart

第二步 配置国内源 及更新软件包

deb http://mirrors.ustc.edu.cn/debian/ bullseye main contrib non-free
deb-src http://mirrors.ustc.edu.cn/debian/ bullseye main contrib non-free
deb http://mirrors.ustc.edu.cn/debian/ bullseye-updates main contrib non-free
deb-src http://mirrors.ustc.edu.cn/debian/ bullseye-updates main contrib non-free
deb http://mirrors.ustc.edu.cn/debian/ bullseye-backports main contrib non-free
deb-src http://mirrors.ustc.edu.cn/debian/ bullseye-backports main contrib non-free

apt update

apt upgrade

第三步 查看python环境 以便做本机测试

python3 --version
# Python 3.9.2  可以满足测试 无需上级

pip3 --versin
# -bash: pip3：未找到命令

# 安装pip3
apt install python3-pip -y

pip3 --version
# pip 20.3.4 from /usr/lib/python3/dist-packages/pip (python 3.9) 正常

# 安装python虚拟环境模块
apt install python3-venv

# 修改pip的源
mkdir ~/.pip
echo "[global]
index-url = https://pypi.tuna.tsinghua.edu.cn/simple" > ~/.pip/pip.conf

第四步 安装docker

apt install apt-transport-https ca-certificates curl gnupg lsb-release wget

curl -fsSL https://download.docker.com/linux/debian/gpg |  gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg

echo  "deb [arch=amd64 signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] http://download.docker.com/linux/debian   $(lsb_release -cs) stable" |  tee /etc/apt/sources.list.d/docker.list > /dev/null

apt update

apt install docker-ce docker-ce-cli containerd.io

docker --version
# Docker version 27.3.1, build ce12230 表示成功

第五步 拉去FunASR镜像

docker pull  registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.4.6

mkdir -p /var/local/funasr-runtime-resources/models

docker run -p 10095:10095 -it --privileged=true -v /var/local/funasr-runtime-resources/models/funasr-runtime-resources/models:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.4.6

cd FunASR/runtime


nohup bash run_server.sh   --download-model-dir /workspace/models --vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx --model-dir damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx --punc-dir damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx --lm-dir damo/speech_ngram_lm_zh-cn-ai-wesp-fst  --itn-dir thuduj12/fst_itn_zh  --hotword /workspace/models/hotwords.txt > log.txt 2>&1 &

# 如果您想关闭ssl，增加参数：--certfile 0
# 如果您想使用SenseVoiceSmall模型、时间戳、nn热词模型进行部署，请设置--model-dir为对应模型：
#   iic/SenseVoiceSmall-onnx
#   damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx（时间戳）
#   damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404-onnx（nn热词）
# 如果您想在服务端加载热词，请在宿主机文件./funasr-runtime-resources/models/hotwords.txt配置热词（docker映射地址为/workspace/models/hotwords.txt）:
#   每行一个热词，格式(热词 权重)：阿里巴巴 20（注：热词理论上无限制，但为了兼顾性能和效果，建议热词长度不超过10，个数不超过1k，权重1~100）
# SenseVoiceSmall-onnx识别结果中"<|zh|><|NEUTRAL|><|Speech|> "分别为对应的语种、情感、事件信息


#部署8k的模型，请使用如下命令启动服务：

cd FunASR/runtime

nohup bash run_server.sh --download-model-dir /workspace/models  --vad-dir damo/speech_fsmn_vad_zh-cn-8k-common-onnx  --model-dir damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1-onnx --punc-dir damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx  --lm-dir damo/speech_ngram_lm_zh-cn-ai-wesp-fst-token8358 --itn-dir thuduj12/fst_itn_zh --hotword /workspace/models/hotwords.txt > log.txt 2>&1 &

第六步 测试

本机测试

# 环境
# python 3.9.X  pip 20及以上

cd /opt

wget https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/sample/funasr_samples.tar.gz

tar xvfz funasr_samples.tar.gz

cd /opt/samples/python

pip3 install websockets

# 第一次测试

python3 funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav"  
-audio_in "../audio/asr_example.wav" --output_dir "./results"

# Namespace(host='127.0.0.1', port=10095, chunk_size=[5, 10, 5], chunk_interval=10, hotword='', audio_in='../audio/asr_example.wav', audio_fs=16000, send_without_sleep=True, thread_num=1, words_max_print=10000, output_dir='./results', ssl=1, use_itn=1, mode='offline')
# connect to wss://127.0.0.1:10095
#pid0_0: demo: 欢迎大家来体验达摩院推出的语音识别模型。 timestamp: [[880,1120],[1120,1380],[1380,1540],[1540,1780],[1780,2020],[2020,2180],[2180,2480],[2480,2600],[2600,2780],[2780,3040],[3040,3240],[3240,3480],[3480,3699],[3699,3900],[3900,4180],[4180,4420],[4420,4620],[4620,4780],[4780,5195]]
#Exception: sent 1000 (OK); then received 1000 (OK)
#end

# 第二次测试

 python3 funasr_wss_client.py --host "192.168.1.181" --port 10095 --mode offline --audio_in "../audio/asr_example.wav" --output_dir "./results"
 
 
# Namespace(host='192.168.1.181', port=10095, chunk_size=[5, 10, 5], chunk_interval=10, hotword='', audio_in='../audio/asr_example.wav', audio_fs=16000, send_without_sleep=True, thread_num=1, words_max_print=10000, output_dir='./results', ssl=1, use_itn=1, mode='offline')
# connect to wss://192.168.1.181:10095
# pid0_0: demo: 欢迎大家来体验达摩院推出的语音识别模型。 timestamp: [[880,1120],[1120,1380],[1380,1540],[1540,1780],[1780,2020],[2020,2180],[2180,2480],[2480,2600],[2600,2780],[2780,3040],[3040,3240],[3240,3480],[3480,3699],[3699,3900],[3900,4180],[4180,4420],[4420,4620],[4620,4780],[4780,5195]]
# Exception: sent 1000 (OK); then received 1000 (OK)
# end

同局域网测试

• python环境

  python3 funasr_wss_client.py --host "192.168.1.181" --port 10095 --mode offline --audio_in "./001.wav" --output_dir "./results"
  
  #  --audio_in "./001.wav"  更改为本机音频路径
  
  # Namespace(host='192.168.1.181', port=10095, chunk_size=[5, 10, 5], chunk_interval=10, hotword='', audio_in='./001.wav', audio_fs=16000, send_without_sleep=True, thread_num=1, words_max_print=10000, output_dir='./results', ssl=1, use_itn=1, mode='offline')
  
  # Namespace(host='192.168.1.181', port=10095, chunk_size=[5, 10, 5], chunk_interval=10, hotword='', audio_in='./001.wav', audio_fs=16000, send_without_sleep=True, thread_num=1, words_max_print=10000, output_dir='./results', ssl=1, use_itn=1, mode='offline')
  # connect to wss://192.168.1.181:10095
  # pid0_0: demo: 咱们是微信支付的，不是银行这边的。 timestamp: [[90,210],[210,290],[290,410],[410,550],[550,690],[690,850],[850,1030],[1030,1310],[1310,1430],[1430,1570],[1570,1670],[1670,1850],[1850,1950],[1950,2130],[2130,2305]]
  # Exception: sent 1000 (OK); then received 1000 (OK)
  # end

• html测试

  打开下载的测试包，打开html/static/index.html
  
  

结束