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
-