New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

"INFO: Nothing has been said or transcribed."报错 #39

Closed
mindcont opened this Issue May 12, 2018 · 8 comments

Comments

Projects
None yet
4 participants
@mindcont

mindcont commented May 12, 2018

我的硬件

PS3 Eye - PS3 淘汰的配件,包含四阵列麦克风和摄像头

本地声卡 cat /proc/asound/cards

pi@raspberrypi:~ $ cat /proc/asound/cards
 0 [ALSA           ]: bcm2835_alsa - bcm2835 ALSA
                      bcm2835 ALSA
 1 [CameraB409241  ]: USB-Audio - USB Camera-B4.09.24.1
                      OmniVision Technologies, Inc. USB Camera-B4.09.24.1 at usb-3f980000.usb-1.5, hi

播放设备 aplay -l , 我想使用 card 0 device 1 bcm2835 IEC958/HDM , 即 HDMI 显示器播放

pi@raspberrypi:~ $ aplay -l
**** List of PLAYBACK Hardware Devices ****
card 0: ALSA [bcm2835 ALSA], device 0: bcm2835 ALSA [bcm2835 ALSA]
  Subdevices: 7/7
  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
card 0: ALSA [bcm2835 ALSA], device 1: bcm2835 ALSA [bcm2835 IEC958/HDMI]
  Subdevices: 1/1
  Subdevice #0: subdevice #0

录音设备arecord -l , 我想使用 card 1 device 0, 即 USB Audio [USB Audio]

pi@raspberrypi:~ $ arecord -l
**** List of CAPTURE Hardware Devices ****
card 1: CameraB409241 [USB Camera-B4.09.24.1], device 0: USB Audio [USB Audio]
  Subdevices: 1/1
  Subdevice #0: subdevice #0

我的配置文件

~/.asoundrc 配置文件

pcm.!default {
        type asym
            playback.pcm {
                type plug
                slave.pcm "hw:0,1"
            }
            capture.pcm {
                type plug
                slave.pcm "hw:1,0"
            }
}

ctl.!default {
        type hw
        card 0
}

默认叮当唤醒词, 使用阿里云 语音合成,已申请key, 引导语 正常.
.dingdang/profile.yml 部分配置

# 语音合成服务配置
# 可选值:
# baidu-tts     - 百度语音识别
# iflytek-tts   - 讯飞语音合成
# ali-tts       - 阿里语音合成
# google-tts    - 谷歌语音合成
tts_engine: ali-tts

# STT 服务配置
# 可选值:
# sphinx        - pocketsphinx离线识别引擎(需训练,参考修改唤醒词教程)
# baidu-stt     - 百度在线语音识别
# iflytek-stt   - 讯飞语音识别
# ali-stt       - 阿里语音识别
# google-stt    - 谷歌语音合成
stt_engine: ali-stt

# 离线唤醒 SST 引擎
# 可选值:
# sphinx        - pocketspinx离线唤醒
# snowboy-stt   - snowboy离线唤醒
stt_passive_engine: sphinx

# pocketsphinx 唤醒SST引擎(默认)
pocketsphinx:
    fst_model: '/home/pi/iot/dingdang/vocabularies/g014b2b/g014b2b.fst'

# snowboy 唤醒SST引擎(可选)
# https://snowboy.kitt.ai/dashboard
snowboy:
    model: '/home/pi/iot/dingdang/client/snowboy/dingdangdingdang.pmdl'  # 唤醒词模型
    sensitivity: "0.5"  # 敏感度

bug 描述

使用 arecord -D plughw:1,0 -d 3 a.wav 正常录音,而使用arecord -d 3 a.wav失败
启动 python dingdang.py -v 报错INFO: Nothing has been said or transcribed.

@wzpan

This comment has been minimized.

Contributor

wzpan commented May 20, 2018

看起来配置是ok的,检查下这个 .asoundrc 是不是没起作用?比如,文件权限?

@mindcont

This comment has been minimized.

mindcont commented May 20, 2018

@wzpan 感谢你的回复

是的.asoundrc没有起作用,我本地的权限是这样的:

pi@raspberrypi:~ $ ls -all | grep .as
-rwxrwxr-x  1 pi   pi     292 May 12 19:43 .asoundrc

我的系统是树莓派 stretch 9, 其中alsa-utils默认配置文件位置在/usr/share/alsa/alsa.conf ,我应该如何查找原因呢?

@wzpan

This comment has been minimized.

Contributor

wzpan commented May 23, 2018

INFO: Nothing has been said or transcribed.

这个并不是报错,只是没有检测到唤醒词。你用的是什么唤醒词?默认的是“嘿叮当”。

@mindcont

This comment has been minimized.

mindcont commented May 24, 2018

我采用的默认唤醒词“嘿叮当” 但是没有反应,我估计还是 录音配置文件.asoundrc的问题,dingdang中有类似录音测试的方法吗

@wzpan

This comment has been minimized.

Contributor

wzpan commented Jun 20, 2018

@mindcont 问题解决了吗?

@mindcont

This comment has been minimized.

mindcont commented Jun 20, 2018

感谢回访,一直闲着没弄,应该是录音 配置文件.asoundrc问题,过几天再试试。
欢迎来我的 无线IO | 一个开源智能家居解决方案 转转😋

@mindcont mindcont closed this Jun 20, 2018

@yuanfengz

This comment has been minimized.

yuanfengz commented Sep 5, 2018

@wzpan 运行dingdang.py微信登录可以发指令回复和聊天,但是直接对麦克风说唤醒词,只会回复“什么”,然后就没什么反映了,这是什么原因呢?(用命令录音和播放录音都没什么问题)

@flydragon2018

This comment has been minimized.

flydragon2018 commented Sep 27, 2018

遇到同样问题。 对着麦克风说,没有效果。有ps eye 的驱动吗?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment