项目作者: toryano0820

项目描述 :
Voice Activity Detection Tool with Waveform Renderer
高级语言: C#
项目地址: git://github.com/toryano0820/VAD-Studio.git
创建时间: 2020-07-11T15:20:06Z
项目社区:https://github.com/toryano0820/VAD-Studio

开源协议:

下载


Voice Activity Detection (VAD) Tool

Features:

  1. Automatically convert from video/audio to required WAV format
  2. Zoomable waveform renderer
  3. Control audio chunk durations directly from Waveform

Developer Instructions:

  1. Edit SttClient.cs to enable STT feature

User Instructions:

  1. Click File -> New (Ctrl + N) menu to opens New Project Dialog
  • Keep or change Project Name
  • Keep or change Project Base Location
  • Choose media file to load
  1. Click Project -> Split menu or Split button to start VAD process
  2. Click Project -> Batch STT menu or Batch STT button to convert audio chunks generated by VAD process into text
  3. Edit chunk text if desired
  4. Click Project -> Batch Export menu or Batch Export button to export audio chunk to WAV file and record text information to sentence_map.csv
  5. Click Reveal button (button in the middle that shows WAV filename) to show project location in Windows Explorer
  6. Click File -> Save (Ctrl + S) menu to save project changes (you can save at any point in this instructions)