baicai-1145
|
6a427b4f54
|
Update TTS API to support asynchronous execution by replacing synchronous TTS calls with asynchronous counterparts in both api_v2.py and api_v3.py. Introduce new data classes in unified_engine.py for enhanced request handling and state management, improving overall system performance and maintainability.
|
2026-03-10 21:25:14 +08:00 |
|
baicai-1145
|
d1a97fd04d
|
Refactor TTS API to streamline audio processing by removing unused packing functions and optimizing the tts_handle method for asynchronous execution. Update type hints and clean up imports for improved code clarity and maintainability.
|
2026-03-10 20:46:14 +08:00 |
|
baicai-1145
|
69ac7f9027
|
Integrate UnifiedTTSEngine into TTS API for improved audio processing and control. Refactor tts_handle and control endpoints to utilize the new engine, enhancing error handling and response management. Update set_refer_audio and set_gpt_weights endpoints to return payloads from the engine, streamlining audio configuration processes.
|
2026-03-10 06:59:28 +08:00 |
|
baicai-1145
|
827d6ea47c
|
Refactor TTS and scheduler components to enhance text processing and batching capabilities. Introduce PrepareCoordinator for managing text feature preparation asynchronously, and update SchedulerDebugWorker to support new finalize task management. Implement batch processing in PrepareBertBatchWorker with improved admission control and profiling metrics. Add text CPU preprocessing utilities for better text segmentation and normalization.
|
2026-03-10 06:58:53 +08:00 |
|
baicai-1145
|
845b181360
|
Implement batch processing for BERT and reference semantic tasks in TTS. Introduce StageLimiter for managing concurrent processing and enhance the TTS class with new methods for handling audio and semantic extraction. Update profiling metrics for better performance tracking during inference.
|
2026-03-09 05:19:28 +08:00 |
|
baicai-1145
|
dc37b0b9ef
|
Add WebAPI documentation and implement TTS API with endpoints for text-to-speech inference, control commands, and model switching. Enhance TTS class with methods for extracting prompt semantics and reference audio specifications. Introduce a scheduler prototype for managing T2S requests.
|
2026-03-09 00:22:59 +08:00 |
|