yaya-sy /
specspeech
Speculative Decoding for fast ASR and TTS inference
Updated 37 min ago
+2 stars gained this week
Stars gained each day, last 30 days
Oct 4Oct 19Today
This week Before
In short
It runs on NVIDIA GPUs with CUDA 13 drivers and Python 3.12 to 3.14, and can be started as an OpenAI-compatible endpoint or used from the command line on audio files or folders.
Summary written by AI from the repository’s description and README.
yaya-sy / specspeech
View on GitHub(opens in new tab)