Jong Wook Kim 31243bad24 Release 20250625

2025-06-25 18:00:48 -07:00

..

assets

large-v3 (#1761)

2023-11-06 10:10:30 -08:00

normalizers

pre-commit autoupdate && pre-commit run --all-files (#2484)

2025-01-04 01:02:18 -08:00

__init__.py

Fix: Update torch.load to use weights_only=True to prevent security w… (#2451)

2025-06-25 17:54:30 -07:00

__main__.py

apply formatting with black (#1038)

2023-03-06 15:50:37 -08:00

audio.py

Updating README and doc strings to reflect that n_mels can now be 128 (#2049)

2024-11-26 09:37:01 -08:00

decoding.py

large-v3 (#1761)

2023-11-06 10:10:30 -08:00

model.py

using sdpa if available (#2359)

2024-09-30 10:27:14 -07:00

timing.py

Fix: Ensure DTW cost tensor is on the same device as input tensor (#2561)

2025-06-25 17:42:09 -07:00

tokenizer.py

large-v3 (#1761)

2023-11-06 10:10:30 -08:00

transcribe.py

Bugfix: Illogical "Avoid computing higher temperatures on no_speech" (#1903)

2024-11-30 21:47:01 -08:00

triton_ops.py

Fixed triton kernel update to support latest triton versions (#2588)

2025-06-25 17:02:54 -07:00

utils.py

pre-commit autoupdate && pre-commit run --all-files (#2484)

2025-01-04 01:02:18 -08:00

version.py

Release 20250625

2025-06-25 18:00:48 -07:00