JohnnySn0w/Echo

Issues

• Wake word detection.

  #4 opened 4 months ago by JohnnySn0w
  1

• train a better wakeword model

  #19 opened 8 months ago by JohnnySn0w
  0

• Split audio generation for LLM response if too large

  #18 opened 8 months ago by JohnnySn0w
  0

• dynamically detect the user has stopped speaking

  #17 opened 8 months ago by JohnnySn0w
  0

• Subprocess speech output

  #16 opened 8 months ago by JohnnySn0w
  0

• RAG integration

  #14 opened 9 months ago by JohnnySn0w
  0

• Windows support

  #7 opened 9 months ago by JohnnySn0w
  2

• Load piper into RAM/VRAM for persistence (remove model load time)

  #1 opened 9 months ago by JohnnySn0w
  0

• Custom Commands

  #12 opened 10 months ago by JohnnySn0w
  0

• More naturalistic responses in the voice output

  #3 opened 10 months ago by JohnnySn0w
  0

• Portability

  #5 opened 10 months ago by JohnnySn0w
  1

• Fine tuning parameters of various components to optimize processing times

  #6 opened 10 months ago by JohnnySn0w
  0

• Setup piper to use AMD GPU (requires custom builds of underlying libs like onnxruntime)

  #2 opened 10 months ago by JohnnySn0w
  0

• Get Echo running on OSX

  #11 opened 10 months ago by JohnnySn0w
  0