RaspberryPi + Pocketsphinx + ps3eye错误:无法打开音频设备

时间:2013-07-22 00:59:51

标签: audio speech-recognition raspberry-pi speech-to-text cmusphinx

刚刚在我的覆盆子pi上安装了pocketsphinx。我觉得我疯了但不确定我是否提供了正确的设备。

每当我跑:

  

src / programs / pocketsphinx_continuous -adcdev plughw:1,0 -nfft 2048   -samprate 48000

我得到以下内容:

  

根@ scarlettpi:/usr/install/pocketsphinx-0.8#   src / programs / pocketsphinx_continuous -adcdev plughw:1,0 -nfft 2048   -samprate 48000 INFO:cmd_ln.c(691):解析命令行:/usr/install/pocketsphinx-0.8/src/programs/.libs/lt-pocketsphinx_continuous   \ -adcdev plughw:1,0 \ -nfft 2048 \ -samprate 48000

     

当前配置:[NAME] [DEFLT] [VALUE]   -adcdev plughw:1,0   -agc none none   -agcthresh 2.0 2.000000e + 00   -alpha 0.97 9.700000e-01   -argfile
  -ascale 20.0 2.000000e + 01   -aw 1 1    - 回溯否否   -beam 1e-48 1.000000e-48   -bestpath是的   -bestpathlw 9.5 9.500000e + 00    - 不,没有   -ceplen 13 13   -cmn电流   -cmninit 8.0 8.0   -compallsen no no   -debug 0   -dict
  -dictcase no no    - 不,不   -doublebw不,不   -ds 1 1   -fdict
  -feat 1s_c_d_dd 1s_c_d_dd   -featparams
  -fillprob 1e-8 1.000000e-08    - 100 100   -fsg
  -fsgusealtpron是的   -fsgusefiller是的   -fwdflat是的   -fwdflatbeam 1e-64 1.000000e-64   -fwdflatefwid 4 4   -fwdflatlw 8.5 8.500000e + 00   -fwdflatsfwin 25 25   -fwdflatwbeam 7e-29 7.000000e-29   -fwdtree是的   -hmm
  -infile
  -input_endian有点小   -jsgf
  -kdmaxbbi -1 -1   -kdmaxdepth 0 0   -kdtree
  -latsize 5000 5000   -lda
  -ldadim 0 0   -lextreedump 0 0   -lifter 0 0   -lm
  -lmctl
  -lmname默认默认值   -logbase 1.0001 1.000100e + 00   -logfn
  -logspec no no   -lowerf 133.33334 1.333333e + 02   -lpbeam 1e-40 1.000000e-40   -lponlybeam 7e-29 7.000000e-29   -lw 6.5 6.500000e + 00   -maxhmmpf -1 -1   -maxnewoov 20 20   -maxwpf -1 -1   -mdef
  -mean
  -mfclogdir
  -min_endfr 0 0   -mixw
  -mixwfloor 0.0000001 1.000000e-07   -mllr
  -mmap是的   -ncep 13 13   -nfft 512 2048   -nfilt 40 40   -nwpen 1.0 1.000000e + 00   -pbeam 1e-48 1.000000e-48   -pip 1.0 1.000000e + 00   -pl_beam 1e-10 1.000000e-10   -pl_pbeam 1e-5 1.000000e-05   -pl_window 0 0   -rawlogdir
  -remove_dc没有没有   -round_filters是的   -samprate 16000 4.800000e + 04    - 种子-1 -1   -sendump
  -senlogdir
  -senmgau
  -silprob 0.005 5.000000e-03   -smoothspec no no   -svspec
   - 没有没有   -tmat
  -tmatfloor 0.0001 1.000000e-04   -topn 4 4   -topn_beam 0 0   -toprule
   - 转变传统遗产   -unit_area是的   -upperf 6855.4976 6.855498e + 03   -usewdphones no no   -uw 1.0 1.000000e + 00   -var
  -varfloor 0.0001 1.000000e-04   -varnorm no no    - 不,不   -warp_params
  -warp_type inverse_linear inverse_linear   -wbeam 7e-29 7.000000e-29   -wip 0.65 6.500000e-01   -wlen 0.025625 2.562500e-02

     

INFO:cmd_ln.c(691):解析命令行:\ -nfilt 20 \ -lowerf 1 \     -upperf 4000 \ -wlen 0.025 \ -transform dct \ -round_filters no \     -remove_dc yes \ -svspec 0-12 / 13-25 / 26-38 \ -feat 1s_c_d_dd \ -agc   none \ -cmn current \ -cmninit 56,-3,1 \ -varnorm no

     

当前配置:[NAME] [DEFLT] [VALUE]   -agc none none   -agcthresh 2.0 2.000000e + 00   -alpha 0.97 9.700000e-01   -ceplen 13 13   -cmn电流   -cmninit 8.0 56,-3,1    - 不,不   -doublebw不,不   -feat 1s_c_d_dd 1s_c_d_dd    - 100 100   -input_endian有点小   -lda
  -ldadim 0 0   -lifter 0 0   -logspec no no   -lowerf 133.33334 1.000000e + 00   -ncep 13 13   -nfft 512 2048   -nfilt 40 20   -remove_dc没有   -round_filters是的   -samprate 16000 4.800000e + 04    - 种子-1 -1   -smoothspec no no   -svspec 0-12 / 13-25 / 26-38    - 转换传统dct   -unit_area是的   -upperf 6855.4976 4.000000e + 03   -varnorm no no    - 不,不   -warp_params
  -warp_type inverse_linear inverse_linear   -wlen 0.025625 2.500000e-02

     

INFO:acmod.c(246):从中解析模型特定的特征参数   /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/feat.params   INFO:feat.c(713):初始化要输入的要素流:' 1s_c_d_dd',   ceplen = 13,CMN ='当前',VARNORM =' no',AGC ='无'信息:cmn.c(142):   mean [0] = 12.00,mean [1..12] = 0.0 INFO:acmod.c(167):使用子向量   规范0-12 / 13-25 / 26-38信息:mdef.c(517):阅读模型   定义:   / usr / local / share / pocketsphinx / model / hmm / en_US / hub4wsj_sc_8k / mdef信息:   mdef.c(528):找到字节顺序标记BMDF,假设这是二进制   mdef文件INFO:bin_mdef.c(336):读取二进制模型定义:   / usr / local / share / pocketsphinx / model / hmm / en_US / hub4wsj_sc_8k / mdef信息:   bin_mdef.c(513):50 CI-phone,143047 CD-phone,3 emitstate / phone,150   CI-sen,5150 Sen,27135 Sen-Seq INFO:tmat.c(205):阅读HMM   转移概率矩阵:   在/ usr / local / share下/ pocketsphinx /模型/哼/ EN_US / hub4wsj_sc_8k / transition_matrices   INFO:acmod.c(121):尝试使用SCHMM计算模块INFO:   ms_gauden.c(198):读取混合高斯参数:   的/ usr /本地/共享/ pocketsphinx /模型/ HMM / EN_US / hub4wsj_sc_8k /装置   信息:ms_gauden.c(292):1个码本,3个特征,大小:信息:   ms_gauden.c(294):256x13 INFO:ms_gauden.c(294):256x13信息:   ms_gauden.c(294):256x13 INFO:ms_gauden.c(198):读取混合物   高斯参数:   在/ usr / local / share下/ pocketsphinx /模型/哼/ EN_US / hub4wsj_sc_8k /方差   信息:ms_gauden.c(292):1个码本,3个特征,大小:信息:   ms_gauden.c(294):256x13 INFO:ms_gauden.c(294):256x13信息:   ms_gauden.c(294):256x13 INFO:ms_gauden.c(354):0方差值   floored INFO:s2_semi_mgau.c(903):从转储文件加载senones   在/ usr / local / share下/ pocketsphinx /模型/哼/ EN_US / hub4wsj_sc_8k / sendump   信息:s2_semi_mgau.c(927):开始文件格式说明信息:   s2_semi_mgau.c(1022):为senone使用内存映射I / O INFO:   s2_semi_mgau.c(1296):最大前N:4前N个波束:0 0 0信息:   dict.c(317):为单词条目分配137543 * 20字节(2686 KiB)   INFO:dict.c(332):阅读主词典:   /usr/local/share/pocketsphinx/model/lm/en_US/cmu07a.dic信息:   dict.c(211):为字符串分配1010 KiB,为手机分配1664 KiB INFO:   dict.c(335):133436 words read INFO:dict.c(341):读取填充符   字典:   在/ usr / local / share下/ pocketsphinx /模型/哼/ EN_US / hub4wsj_sc_8k / noisedict   INFO:dict.c(211):为字符串分配0 KiB,为手机分配0 KiB INFO:   dict.c(344):11个字读取信息:dict2pid.c(396):构建PID表   对于字典信息:dict2pid.c(404):分配50 ^ 3 * 2字节(244   单词初始三音素的KiB)信息:dict2pid.c(131):分配30200   单词最终三音素的字节数(29 KiB)INFO:dict2pid.c(195):   为单电话三字电话分配30200字节(29 KiB)INFO:   ngram_model_arpa.c(77):LM文件INFO中没有\ data \标记:   ngram_model_dmp.c(142):对LM文件INFO使用内存映射I / O:   ngram_model_dmp.c(196):ngrams 1 = 5001,2 = 436879,3 = 418286信息:   ngram_model_dmp.c(242):5001 = LM.unigrams(+ trailer)读取信息:   ngram_model_dmp.c(288):436879 = LM.bigrams(+ trailer)阅读信息:   ngram_model_dmp.c(314):418286 = LM.trigrams读取信息:   ngram_model_dmp.c(339):37293 = LM.prob2条目读取信息:   ngram_model_dmp.c(359):14370 = LM.bo_wt2条目读取信息:   ngram_model_dmp.c(379):36094 = LM.prob3条目读取信息:   ngram_model_dmp.c(407):854 = LM.tseg_base条目读取信息:   ngram_model_dmp.c(463):5001 = ascii字符串读取信息:   ngram_search_fwdtree.c(99):788个独特的初始双音素信息:   ngram_search_fwdtree.c(147):0个根,0个非根通道,60   单个电话词INFO:ngram_search_fwdtree.c(186):创建搜索   tree INFO:ngram_search_fwdtree.c(191):before:0 root,0 non-root   频道,60个单个电话词INFO:ngram_search_fwdtree.c(326):   之后:max nonroot chan增加到13428 INFO:   ngram_search_fwdtree.c(338):after:457 root,13300个非root通道,   26个单电话字INFO:ngram_search_fwdflat.c(156):fwdflat:   min_ef_width = 4,max_sf_win = 25 INFO:continuous.c(371):   /usr/install/pocketsphinx-0.8/src/programs/.libs/lt-pocketsphinx_continuous   编译日期:2013年7月21日,AT:14:34:06

     

混音器加载失败:无效参数FATAL_ERROR:" continuous.c",line   246:无法打开音频设备

我目前正在使用ps3eye。如果我做一个简单的事情:

  

arecord -D plughw:1,0 -d 5 -q -f cd -t wav~ / test.wav

一切正常(通过HDMI将Raspberrypi连接到电视并运行播放〜/ test.wav验证了这一点)

我做错了什么?

您可能需要的信息(基于我见过的其他帖子):

root@scarlettpi:/usr/install/pocketsphinx-0.8# aplay -l
**** List of PLAYBACK Hardware Devices ****
card 0: ALSA [bcm2835 ALSA], device 0: bcm2835 ALSA [bcm2835 ALSA]
  Subdevices: 8/8
  Subdevice #0: subdevice #0
  Subdevice #1: subdevice #1
  Subdevice #2: subdevice #2
  Subdevice #3: subdevice #3
  Subdevice #4: subdevice #4
  Subdevice #5: subdevice #5
  Subdevice #6: subdevice #6
  Subdevice #7: subdevice #7
root@scarlettpi:/usr/install/pocketsphinx-0.8# 
root@scarlettpi:/usr/install/pocketsphinx-0.8# aplay -L
null
    Discard all samples (playback) or generate zero samples (capture)
pulse
    PulseAudio Sound Server
sysdefault:CARD=ALSA
    bcm2835 ALSA, bcm2835 ALSA
    Default Audio Device
root@scarlettpi:/usr/install/pocketsphinx-0.8#



root@scarlettpi:/usr/install/pocketsphinx-0.8# dpkg -l | grep "alsa"
ii  alsa-base                             1.0.25+3~deb7u1                      all          ALSA driver configuration files
ii  alsa-firmware-loaders                 1.0.25-2                             armhf        ALSA software loaders for specific hardware
ii  alsa-oss                              1.0.25-1                             armhf        ALSA wrapper for OSS applications
ii  alsa-tools                            1.0.25-2                             armhf        Console based ALSA utilities for specific hardware
ii  alsa-utils                            1.0.25-4                             armhf        Utilities for configuring and using ALSA
ii  alsaplayer-alsa                       0.99.80-5.1                          armhf        PCM player designed for ALSA (ALSA output module)
ii  alsaplayer-common                     0.99.80-5.1                          armhf        PCM player designed for ALSA (common files)
ii  alsaplayer-gtk                        0.99.80-5.1                          armhf        PCM player designed for ALSA (GTK+ version)
ii  gstreamer0.10-alsa:armhf              0.10.36-1.1                          armhf        GStreamer plugin for ALSA
ii  libsox-fmt-alsa                       14.4.0-3                             armhf        SoX alsa format I/O library
root@scarlettpi:/usr/install/pocketsphinx-0.8#



root@scarlettpi:/usr/install/pocketsphinx-0.8# dpkg -l | grep pulseaudio
ii  gstreamer0.10-pulseaudio:armhf        0.10.31-3+nmu1                       armhf        GStreamer plugin for PulseAudio
root@scarlettpi:/usr/install/pocketsphinx-0.8# 

另外,在安装口袋狮身人面像方面,我做了以下几点:

# uninstall pulse audio if its already installed 
apt-get remove pulseaudio -y 
aptitude purge pulseaudio -y

# sphinxbase install
apt-get install bison -y
cd /usr/install
wget  http://downloads.sourceforge.net/project/cmusphinx/sphinxbase/0.8/sphinxbase-0.8.tar.gz
tar -xvf sphinxbase-0.8.tar.gz
cd sphinxbase-0.8
./configure
make
make install
cd -

# pocketsphinx installwget http://sourceforge.net/projects/cmusphinx/files/pocketsphinx/0.8/pocketsphinx-0.8.tar.gz
tar -xvf pocketsphinx-0.8.tar.gz
cd pocketsphinx-0.8
./configure
make
make install

任何正确方向的想法或建议都会非常有用。

谢谢,

Malcolm Jones

编辑:

忘记包含此信息:

root@scarlettpi:/usr/install/pocketsphinx-0.8# arecord -L
null
    Discard all samples (playback) or generate zero samples (capture)
pulse
    PulseAudio Sound Server
sysdefault:CARD=CameraB409241
    USB Camera-B4.09.24.1, USB Audio
    Default Audio Device
front:CARD=CameraB409241,DEV=0
    USB Camera-B4.09.24.1, USB Audio
    Front speakers
surround40:CARD=CameraB409241,DEV=0
    USB Camera-B4.09.24.1, USB Audio
    4.0 Surround output to Front and Rear speakers
surround41:CARD=CameraB409241,DEV=0
    USB Camera-B4.09.24.1, USB Audio
    4.1 Surround output to Front, Rear and Subwoofer speakers
surround50:CARD=CameraB409241,DEV=0
    USB Camera-B4.09.24.1, USB Audio
    5.0 Surround output to Front, Center and Rear speakers
surround51:CARD=CameraB409241,DEV=0
    USB Camera-B4.09.24.1, USB Audio
    5.1 Surround output to Front, Center, Rear and Subwoofer speakers
surround71:CARD=CameraB409241,DEV=0
    USB Camera-B4.09.24.1, USB Audio
    7.1 Surround output to Front, Center, Side, Rear and Woofer speakers
iec958:CARD=CameraB409241,DEV=0
    USB Camera-B4.09.24.1, USB Audio
    IEC958 (S/PDIF) Digital Audio Output
root@scarlettpi:/usr/install/pocketsphinx-0.8# 

3 个答案:

答案 0 :(得分:19)

我花了一些时间,在一些来源的帮助下(他们将在我的答案中列出)和nikolay-shmyrev的一些有用提示,我终于想出了一个对我有用的答案。

主要假设:

  1. 以pi用户身份运行这些命令(之前我以root身份运行它们,这是不正确的)

  2. 我正在使用持续识别,我只是在寻找“唤醒”我的覆盆子pi的能力。在醒来之后,我还有其他计划应该如何互动。

  3. 我的设置:

    1. Canakit RaspberryPi

    2. HDMI线缆连接到我的东芝电视

    3. usb wifi dongle

    4. Playstation 3 Eye for Speech recognition

    5. 前进。我在RaspberryPi上运行了以下命令,让PulseAudio + pocketsphinx与我的Playstation 3 Eye一起工作。 (如果您有任何改进的地方请告诉我们)

      安装脉冲音频/开发包

      sudo apt-get install gstreamer0.10-pulseaudio libao4 libasound2-plugins libgconfmm-2.6-1c2 libglademm-2.4-1c2a libpulse-dev libpulse-mainloop-glib0 libpulse-mainloop-glib0-dbg libpulse0 libpulse0-dbg libsox-fmt-pulse paman paprefs pavucontrol pavumeter pulseaudio pulseaudio-dbg pulseaudio-esound-compat pulseaudio-esound-compat-dbg pulseaudio-module-bluetooth pulseaudio-module-gconf pulseaudio-module-jack pulseaudio-module-lirc pulseaudio-module-lirc-dbg pulseaudio-module-x11 pulseaudio-module-zeroconf pulseaudio-module-zeroconf-dbg pulseaudio-utils oss-compat -y
      

      设置ALSA

      来自http://forums.debian.net/viewtopic.php?f=16&t=12497

      的说明
      sudo \cp -pf /etc/asound.conf /etc/asound.conf.ORIG 
      echo 'pcm.pulse {
          type pulse
      }
      
      ctl.pulse {
          type pulse
      }
      
      pcm.!default {
          type pulse
      }
      
      ctl.!default {
          type pulse
      }' | sudo tee /etc/asound.conf
      

      确保您的相机设备在启动时加载

      _DEVICE_LOAD_ON_START=$(grep "snd.bcm2835" /etc/modules | wc -l)
      if [[ "${_DEVICE_LOAD_ON_START}" = "0" ]]; then
      
        sudo \cp -pf /etc/modules /etc/modules.ORIG
        echo "snd-bcm2835" | tee -a /etc/modules
      
      fi
      
      # Disallow module loading after startup. This is a security feature since it disallows additional module loading during runtime and on user request.
      _DISALLOW_MODULE_LOADING=$(grep "DISALLOW_MODULE_LOADING=1" /etc/default/pulseaudio | wc -l)
      if [[ "${_DISALLOW_MODULE_LOADING}" = "0" ]]; then
      
        sudo \cp -pf /etc/default/pulseaudio /etc/default/pulseaudio.ORIG
        sudo sed -i "s,DISALLOW_MODULE_LOADING=1,DISALLOW_MODULE_LOADING=0,g" /etc/default/pulseaudio
      
      fi
      

      为网络连接设置PulseAudio守护程序

      # allow other clients on the network to connect to pulseaudio daemon ( only add auth-anonymous=1 if you know EVERY machine on your LAN ... this could be a security risk otherwise )
      sudo \cp -fvp /etc/pulse/system.pa /etc/pulse/system.pa.ORIG
      echo "
      # ScarlettPi ADDED THIS
      load-module module-native-protocol-tcp auth-ip-acl=127.0.0.1;192.168.0.0/24 auth-anonymous=1
      load-module module-zeroconf-publish" | sudo tee -a /etc/pulse/system.pa
      
      echo "
      # ScarlettPi added this
      #load-module module-native-protocol-tcp
      #load-module module-zeroconf-publish
      load-module module-native-protocol-tcp auth-ip-acl=127.0.0.1;192.168.0.0/24 auth-anonymous=1
      load-module module-zeroconf-publish" | sudo tee -a /etc/pulse/default.pa
      
      # check to make sure it looks okay
      cat /etc/pulse/default.pa
      

      将默认声音驱动程序从alsa更改为pulseaudio

      sudo \cp -fvp /etc/libao.conf /etc/libao.conf.ORIG
      sudo sed -i "s,default_driver=alsa,default_driver=pulse,g" /etc/libao.conf 
      
      # daemon settings according to Pi-Musicbox ( https://github.com/woutervanwijk/Pi-MusicBox )
      sudo \cp -fvp /etc/pulse/daemon.conf /etc/pulse/daemon.conf.ORIG
      
      echo "
      # ScarlettPi added this
      high-priority = yes
      nice-level = 5
      exit-idle-time = -1
      resample-method = src-sinc-medium-quality
      default-sample-format = s16le
      default-sample-rate = 48000
      default-sample-channels = 2" | sudo tee -a /etc/pulse/daemon.conf
      

      pi用户添加到脉冲访问组

      sudo adduser pi pulse-access
      
      # shut down the machine to make sure all the settings we just made are loaded correctly
      sudo shutdown -r now
      

      确保将/usr/local/lib添加到库路径

      export LD_LIBRARY_PATH=/usr/local/lib
      export PKG_CONFIG_PATH=/usr/local/lib/pkgconfig
      
      # also add these to your .bashrc so they get set once you login 
      echo "
      # scarlettPi added this
      export LD_LIBRARY_PATH=/usr/local/lib
      export PKG_CONFIG_PATH=/usr/local/lib/pkgconfig" | tee -a ~/.bashrc
      

      安装基础PocketSphinx

      # install python dev packages
      sudo apt-get install python2.7-dev -y
      
      # sphinxbase install ( required to install pocketsphinx )
      sudo apt-get install bison -y
      cd ~pi/
      wget  http://downloads.sourceforge.net/project/cmusphinx/sphinxbase/0.8/sphinxbase-0.8.tar.gz
      tar -xvf sphinxbase-0.8.tar.gz
      cd sphinxbase-0.8
      ./configure
      make
      sudo make install
      cd -
      
      # pocketsphinx install
      # set this: LD_LIBRARY_PATH=/path/to/pocketsphinxlibs /usr/local/bin/pocketsphinx_continuous
      # http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/howto-use-pocketsphinx
      wget http://sourceforge.net/projects/cmusphinx/files/pocketsphinx/0.8/pocketsphinx-0.8.tar.gz
      tar -xvf pocketsphinx-0.8.tar.gz
      cd pocketsphinx-0.8
      ./configure
      make
      sudo make install
      cd -
      
      # install sphinxtrain
      wget http://sourceforge.net/projects/cmusphinx/files/sphinxtrain/1.0.8/sphinxtrain-1.0.8.tar.gz
      tar -xvf sphinxtrain-1.0.8
      cd sphinxtrain-1.0.8
      ./configure
      make
      sudo make install
      cd -
      

      检查脉冲守护程序是否正在运行

      ps aux | grep pulse
      
      # If it isn't, start it up yourself ( need to figure out the best way to make this run on boot...init.d script maybe? )
      /usr/bin/pulseaudio --start --log-target=syslog --system=false
      

      最后,运行Sphinx

      重要提示 你必须是用户PI和PULSEAUDIO服务器需要运行

      确认现有的语料库文件,.jsgf文件,.dic和.lm文件(使用lmtool

      cd ~pi/pocketsphinx-0.8
      pocketsphinx_continuous -lm /home/pi/scarlettPi/config/speech/lm/scarlett.lm -dict /home/pi/scarlettPi/config/speech/dict/scarlett.dic -hmm /home/pi/scarlettPi/config/speech/model/hmm/en_US/hub4wsj_sc_8k -silprob  0.1 -wip 1e-4 -bestpath 0
      

      参考文献:

      我计划在我的家庭自动化项目的博客文章中添加更多详细信息,说明为什么我使用了某些设置和配置,但想通了,我将分享我到目前为止所做的事情,因为其他人被卡住了像我一样,愿意继续他们的工作。希望这有助于某人。谢谢你的建议。

答案 1 :(得分:2)

  

apt-get remove pulseaudio -y   aptitude purge pulseaudio -y

如果你不知道如何配置alsa,你最好使用pulseaudio,而且,它是在你的系统上配置的。您最好使用pulseaudio支持编译sphinxbase。有关更多信息,请阅读常见问题解答:

http://cmusphinx.sourceforge.net/wiki/faq#qfailed_to_open_audio_device_dev_dsp_no_such_file_or_directory

  

混音器加载失败:参数无效

这是一个关键信息,它表示你的alsa配置不支持电平调音台。如果您不知道如何在alsa配置中添加混音器,请使用pulseaudio

  

./ configure --enable-fixed

这也是一个坏主意,会降低设备的速度和准确性。您的处理器具有FPU,因此您不应使用定点模式。

答案 2 :(得分:1)

我遇到了无法打开音频设备的问题。

http://cmusphinx.sourceforge.net/wiki/faq#qfailed_to_open_audio_device_dev_dsp_no_such_file_or_directory

我修复它购买安装libpulse-dev软件包然后重新安装sphinxbase,pocketsphinx。