tsukumi 08c439e88e Refactor: Use I/O Binding during BERT inference and always release memory after inference

2024-12-22 06:49:43 +09:00

..

utils

Improve: Models can now be loaded directly onto NVIDIA GPUs

2024-09-17 05:23:02 +09:00

__init__.py

Add: empty __init__.py

2024-03-07 09:09:24 +00:00

attentions.py

Format import using isort --profile black --gitignore --lai 2 .

2024-03-11 12:37:51 +09:00

commons.py

Format import using isort --profile black --gitignore --lai 2 .

2024-03-11 12:37:51 +09:00

hyper_parameters.py

Add: Support for ONNX inference and ONNX conversion of Non-JP-Extra models

2024-09-23 05:59:12 +09:00

infer_onnx.py

Refactor: Use I/O Binding during BERT inference and always release memory after inference

2024-12-22 06:49:43 +09:00

infer.py

Improve: ONNX conversion logic improved, and support for noise_scale(_w) model argument

2024-09-22 16:14:25 +09:00

models_jp_extra.py

Fmt only (maybe)

2024-05-25 18:15:36 +09:00

models.py

Fmt only (maybe)

2024-05-25 18:15:36 +09:00

modules.py

Apply black formatter

2024-03-11 09:47:47 +09:00

monotonic_alignment.py

Format import using isort --profile black --gitignore --lai 2 .

2024-03-11 12:37:51 +09:00

transforms.py

Apply black formatter

2024-03-11 09:47:47 +09:00