Vaibhavs10/ml-with-audio

Covers end-to-end audio ML topics including automatic speech recognition, text-to-speech synthesis, source separation, and speaker identification through structured weekly sessions with video presentations and paper discussions. Structured around curated learning paths using foundational resources like Speech & Language Processing alongside hands-on notebooks, with integration to toolkits like SpeechBrain and ESPnet for implementation. Community-driven format encourages collaborative exploration via Discord, with supplementary research papers and interactive Hugging Face Spaces demos for experimentation.

202 stars. No commits in the last 6 months.