Universität, Diversität, Kreativität

dot AI

Speech & Voice

Speech-To-Text (Deepspeech, Whispr)

Text-to-Speech (xTTS, coqui)

Voice Cloning

Singing Voice Generation

Languague Models

Open-Source

Low Rank Adaptation

Fine-tuning

Axiometry

Three pillars

Sustainability

Ethics & Morality

Interpretability

Axiometry

Stay tuned