禾息 62e04e8856 Enhance CosyVoice with CUDA stream management and estimator handling ...

- Introduced a queue-based system for managing CUDA streams to improve inference performance.
- Updated inference methods to utilize CUDA streams for asynchronous processing.
- Added an EstimatorWrapper class to manage TensorRT estimators, allowing for efficient execution context handling.
- Modified model loading functions to support estimator count configuration.
- Improved logging and performance tracking during inference operations.

2025-04-16 11:16:28 +08:00

..

bin

fix lint

2025-01-02 12:32:43 +08:00

cli

Enhance CosyVoice with CUDA stream management and estimator handling

2025-04-16 11:16:28 +08:00

dataset

fix pitch computation

2025-01-23 15:44:03 +08:00

flow

Enhance CosyVoice with CUDA stream management and estimator handling

2025-04-16 11:16:28 +08:00

hifigan

add online trt export

2025-01-10 13:55:05 +08:00

llm

Revert "mv AsyncLLMEngine init to CosyVoice2"

2025-03-21 16:17:35 +08:00

tokenizer

update readme

2024-12-16 14:05:00 +08:00

transformer

fix lint

2024-12-16 10:37:10 +08:00

utils

fix pitch computation

2025-01-23 15:44:03 +08:00

__init__.py

add cosyvoice code

2024-07-04 21:15:12 +08:00