AI Agent Skills

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Agent-led recent-trends research across social, prediction markets, video, code, and the web.

Port of OpenAI's Whisper model in C/C++

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.