16 Commits

Author	SHA1	Message	Date
MasterPhooey	ee6ff6e9d5	micro-opus fix	2026-04-25 08:46:34 -05:00
MasterPhooey	6e7396455a	Automatic Calibration	2026-04-18 09:02:05 -05:00
MasterPhooey	45583027a4	remove recorder/upload samples	2026-04-14 22:55:49 -05:00
MasterPhooey	8ad4b19bc7	debloat	2026-01-21 09:09:06 -06:00
Tater Totterson	8669ccdfd4	Improve CUDA/XLA setup and CPU fallback	2026-01-20 20:47:58 -06:00
MasterPhooey	c52f92d3c9	cli + web recorder ui	2026-01-17 16:23:24 -06:00
MasterPhooey	5bc0f12a7f	cli + web recorder ui	2026-01-17 01:23:51 -06:00
George Joseph	74b36885b5	Switch from nvidia/cuda to plain ubuntu:22.05 base image ... Since this is a pure Python environment, the CUDA toolkit isn't really necessary. The various Python packages that can use CUDA will download and install the CUDA dependencies they need. This shaves off at least 8gb from the final image. The Python package install order needed to be tweaked to ensure onnxruntime, tensorflow and torch are installed in that order. Any other order results in dependent cuda package clashes. Resolves: #12	2025-12-19 10:14:26 -07:00
Tater Totterson	7c9c6f7a88	Add files via upload	2025-12-05 07:44:13 -06:00
Tater Totterson	c6fe612143	Add files via upload	2025-09-27 19:44:55 -05:00
Tater Totterson	cef3daa1a7	cleanup	2025-09-27 14:55:23 -05:00
Tater Totterson	e9d6b8b87e	cleanup	2025-09-27 11:10:43 -05:00
Tater Totterson	3eea499f90	Add files via upload	2025-09-26 19:41:21 -05:00
Tater Totterson	7137c55482	Add files via upload	2025-09-26 19:35:09 -05:00
MasterPhooey	8dcc55e926	add advanced training	2025-01-04 21:18:31 -06:00
MasterPhooey	f911125c6e	Add files via upload	2025-01-03 08:14:57 -06:00