Gabriel de Marmiesse 222714c495 Fix memory leak by using no_grad in all threads (#16) ...

`torch.no_grad` is thread local, I now run the autoregressive generation
in a separate thread, in addition of the thread running mimi, and forgot
to add `torch.no_grad` to the function inside this thread.

2026-01-13 18:07:02 +01:00

..

conditioners

Copy the files in the new repo for public release

2026-01-12 11:25:16 +01:00

config

Copy the files in the new repo for public release

2026-01-12 11:25:16 +01:00

data

Copy the files in the new repo for public release

2026-01-12 11:25:16 +01:00

models

Fix memory leak by using no_grad in all threads (#16)

2026-01-13 18:07:02 +01:00

modules

Use the new checkpoints structure (#10)

2026-01-12 12:56:13 +01:00

static

Fix html

2026-01-13 11:30:33 +01:00

utils

Change voices available without voice cloning (#12)

2026-01-13 11:06:23 +01:00

__init__.py

Copy the files in the new repo for public release

2026-01-12 11:25:16 +01:00

__main__.py

Copy the files in the new repo for public release

2026-01-12 11:25:16 +01:00

default_parameters.py

Change voices available without voice cloning (#12)

2026-01-13 11:06:23 +01:00

main.py

Change voices available without voice cloning (#12)

2026-01-13 11:06:23 +01:00