Thorsten Müller (Youtube)

From Voice Technology Wiki
Revision as of 20:46, 10 December 2021 by Thorsten (talk | contribs) (Added Youtube video links)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

Introduction[edit | edit source]

As OpenVoice enthusiast i thought on sharing my lessons learned and knowledge on Youtube. Nothing fancy or well structured, just sharing thoughts and knowledge.

Videos[edit | edit source]

General[edit | edit source]

  • Create your own TTS Voice with Mycroft Mimic-Recording-Studio and Coqui TTS (Youtube Link)
  • Choose right version of your voice for TTS dataset recording (Youtube Link)
  • Collection of tips and tricks i found on improving your speaker voice (Youtube Link)
  • Identify and remove too fast/slow recordings from your dataset (Youtube Link)

About Mycroft[edit | edit source]

  • Create LJSpeech directory structure from Mimic-RecordingStudio recordings (practical walkthrough) (Youtube Link)
  • Configuring Mycroft AI smart voice assistant to use local Coqui TTS server (Youtube Link)

About Coqui TTS[edit | edit source]

  • Running Coqui TTS in a Docker container on NVIDIA Jetson device (Youtube Link)
  • Setup Coqui TTS server in less than 5 minutes (Youtube Link)
  • Coqui TTS model training configuration (Youtube Link)
  • Setting up Coqui TTS on Google Colab (Youtube Link)
  • Using "AnalyzeDataset" notebook from Coqui TTS (Youtube Link)
  • Running Coqui TTS notebook for waveform SNR analysis (Youtube Link)
  • Introducing cTTS Python module (Youtube Link)

About OpenVoice-Tech Wiki[edit | edit source]