禾息 7f4c9a2c64 Refactor CosyVoice inference methods to streamline CUDA stream management ...

- Removed the queue-based stream pool and integrated direct CUDA stream usage for improved performance.
- Simplified inference methods by eliminating unnecessary synchronization and stream management code.
- Enhanced logging for better tracking of synthesis operations and performance metrics.
- Updated the model class to support CUDA stream context management, ensuring efficient resource utilization during inference.

2025-04-16 14:15:14 +08:00

..

bin

fix lint

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

cli

Refactor CosyVoice inference methods to streamline CUDA stream management

2025-04-16 14:15:14 +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