Difference between revisions of "Speech Recognition"

From Diustou Wiki
 
Line 70: Line 70:
 
=== Firmware Creation ===
 
=== Firmware Creation ===
 
*Go to the [http://www.smartpi.cn/#/ official website], click "Login" or "Register" in the top right corner.
 
*Go to the [http://www.smartpi.cn/#/ official website], click "Login" or "Register" in the top right corner.
−
**[[File:Speech Recognition_固件制作1.png|600px]
+
**[[File:Speech Recognition_固件制作1.png|600px]]
 
*Click "Product Management" -> "All Products" -> "Import Product"
 
*Click "Product Management" -> "All Products" -> "Import Product"
 
**[[File:Speech Recognition_固件制作2.png|600px]]
 
**[[File:Speech Recognition_固件制作2.png|600px]]
Line 83: Line 83:
 
*After successfully saving, click "Back" in the top left corner. For the modified project, click "More" -> "Generate SDK" and wait for the SDK generation to complete.
 
*After successfully saving, click "Back" in the top left corner. For the modified project, click "More" -> "Generate SDK" and wait for the SDK generation to complete.
 
**[[File:Speech Recognition_固件制作9.png|600px]][[File:Speech Recognition_固件制作10.png|600px]][[File:Speech Recognition_固件制作11.png|600px]]
 
**[[File:Speech Recognition_固件制作9.png|600px]][[File:Speech Recognition_固件制作10.png|600px]][[File:Speech Recognition_固件制作11.png|600px]]
 +
 +
== Reference Materials ==
 +
*[https://wiki.diustou.com/cn/%E6%96%87%E4%BB%B6:CH341SER.zip CH340/CH341 USB to Serial Windows Driver]（Supports 32/64-bit Windows 11/10/8.1/8/7/Vista/XP.）
 +
*[https://wiki.diustou.com/cn/%E6%96%87%E4%BB%B6:%E4%B8%B2%E5%8F%A3%E8%B0%83%E8%AF%95%E5%8A%A9%E6%89%8B.zip Serial port debugging assistant.]]
 +
*[http://help.aimachip.com/docs/offline_su03t/offline_su03t-1e9c63ok0doou SU-03T Documentation Web Version]
 +
*[https://wiki.diustou.com/cn/%E6%96%87%E4%BB%B6:Speech_Recognition_SU-03T.zip SU-03T Documentation]
 +
*[https://wiki.diustou.com/cn/%E6%96%87%E4%BB%B6:DSTSR-S_speech_recognition_%E8%AF%AD%E9%9F%B3%E8%AF%86%E5%88%AB%E4%B8%B2%E5%8F%A3%E8%BE%93%E5%87%BA%E5%91%BD%E4%BB%A4.zip Default Serial Port Output Commands]
 +
*[https://wiki.diustou.com/cn/%E6%96%87%E4%BB%B6:Speech_Recognition_%E5%87%BA%E5%8E%82%E5%9B%BA%E4%BB%B61.zip Factory Firmware]
 +
*[https://wiki.diustou.com/cn/%E6%96%87%E4%BB%B6:Speech_Recognition_%E5%9B%BA%E4%BB%B6%E7%83%A7%E5%BD%95%E8%BD%AF%E4%BB%B6.7z Firmware Burning Software]
 +
*[https://wiki.diustou.com/cn/%E6%96%87%E4%BB%B6:Speech_Recognition_%E5%9B%BA%E4%BB%B6%E5%88%B6%E4%BD%9C%E6%8C%87%E5%8D%97.zip Firmware Creation Guide]
  
 
== FAQ ==
 
== FAQ ==
 
{{Service00}}
 
{{Service00}}

Latest revision as of 14:33, 13 January 2025

Speech Recognition
Speech Recognition 示意图.png
Information

Categories: USB UART

Brand: Diustou

Description
Features
  • Speech Recognition

Interfaces

USB UART

Related products

{{{related}}}

Product Parameters

  • Main Control Module: SU-03T
  • Power Supply Interface: Type-C interface or pin header
  • Supply Voltage: 5V
  • Supply Current: >500mA
  • Output Voltage: 5V or 3.3V
    • Internal LDO converts 5V to 3.3V, external load for 3.3V should not exceed 150mA
  • Pin Voltage: 3.3V
  • Power Consumption: Average operating current 60mA
  • Number of IO Ports: 10
  • Speaker Specification: VCC 5V, 8Ω, 3W
  • Supported Interfaces: UART/GPIO/ADC/PWM/SPI/I2S/I2C
    • All GPIOs can be configured as external interrupt inputs and wake-up sources
    • 1 standard SPI interface, max speed 30MHz
    • 1 full-duplex UART, max speed 3Mbps, serial port voltage 3.3V
    • 1 I2C master/slave controller, max speed 400kHz
    • 2 PWM outputs
    • 1 12-bit SAR-ADC, max sampling rate 450Khz
  • 32bit RISC core, operating frequency 240M
  • Supports DSP instruction set and FPU floating-point unit
  • FFT Accelerator: Supports up to 1024-point complex FFT/IFFT operations, or 2048-point real FFT/IFFT operations
  • Built-in high-speed SRAM, 2MB FLASH memory
  • Built-in 2.4W, mono AB class amplifier
  • Built-in POR (Power on Reset), low voltage detection, and watchdog
  • Operating Temperature: -20℃ ~70℃

Product Description

Module Description

  • Speech Recognition 模块说明.png

Pin Description

  • Speech Recognition 引脚说明.png

Usage Instructions

Default Configuration

  • The speech recognition module comes with the Factory Firmware pre-installed. It can output corresponding control commands via Type-C and 4PIN interfaces and control corresponding GPIO ports. Please refer to the table below for specific serial port output and control:
    • Speech Recognition 默认配置.png
  • Wiring method (using USB relay as an example):
    • Speech Recognition 默认配置1.png

Updating Firmware via Serial Port

(make sure there are no Chinese characters in the path)
    • Speech Recognition 串口更新固件1.png
  • Select firmware: \DSTSR-S-formware\for_Dstou_usb_relay_jx_firm\Dstou_usb_relay_release_update.bin
    • Speech Recognition 串口更新固件2.png
  • Update firmware via Type C (disconnect the 4PIN UART wiring), set the DIP switch to the OFF position, plug in the USB cable, and the connected serial port will be displayed in the burning tool.
    • Speech Recognition 串口更新固件3.png
    • Speech Recognition 串口更新固件4.png
  • Click the "Burn" button
    • Speech Recognition 串口更新固件5.png
  • Set the DIP switch on the board to POWER ON to start downloading. If it doesn't work, repeat the operation. Wait for the download to complete.
    • Speech Recognition 串口更新固件6.png
    • Speech Recognition 串口更新固件7.png
  • The download process via the 4PIN UART port is the same as the Type C port.

Firmware Creation

  • Go to the official website, click "Login" or "Register" in the top right corner.
    • Speech Recognition 固件制作1.png
  • Click "Product Management" -> "All Products" -> "Import Product"
    • Speech Recognition 固件制作2.png
  • Select the 语音识别_配合丢石头USB继电器使用_20231205001.json file in the default firmware folder.
    • Speech Recognition 固件制作3.png
  • Click "View Details"
    • Speech Recognition 固件制作4.png
  • Click "View" or "Inherit". (View allows modifications based on the existing project; Inherit creates a copy for modification. If the current project has been published, you must click Inherit to save changes.)
    • Speech Recognition 固件制作5.png
  • Enter the project interface and make modifications as needed. Click "Save" after completing the modifications.
    • Speech Recognition 固件制作6.pngSpeech Recognition 固件制作7.pngSpeech Recognition 固件制作8.png
  • After successfully saving, click "Back" in the top left corner. For the modified project, click "More" -> "Generate SDK" and wait for the SDK generation to complete.
    • Speech Recognition 固件制作9.pngSpeech Recognition 固件制作10.pngSpeech Recognition 固件制作11.png

Reference Materials

FAQ

Icon-mail.png Contact Diustou

Our working hours are: 09:00-18:00 (UTC+8 Monday to Saturday)

Retrieved from "https://wiki.diustou.com/en/index.php?title=Speech_Recognition&oldid=1557"