baicai-1145 c94de2f2cb Enhance TTS audio processing with improved resampling and profiling metrics ...

Refactor the audio preparation workflow to utilize torchaudio for resampling, replacing librosa for better performance. Introduce a caching mechanism for resampling transforms and update the PrepareRefSemanticBatchWorker to include detailed timing metrics for profiling. Additionally, implement a new CPU limiter for managing resource allocation during audio processing. These changes improve the efficiency and maintainability of the TTS system.

2026-03-13 16:45:00 +08:00

..

AR

Enhance sampling functions in TTS by adding support for previous token masks in logits_to_probs. Implement batch processing for sampling with padded token sequences and contiguous sampling groups. Refactor sampling logic in T2S scheduler to utilize new functionalities, improving efficiency and flexibility in token generation.

2026-03-09 21:24:16 +08:00

BigVGAN

Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

2025-04-07 16:42:47 +08:00

configs

优化TTS_Config的代码逻辑 (#2536)

2025-07-18 11:54:40 +08:00

eres2net

Fix bugs in install.sh, reduce log noise, and improve error reporting (#2464)

2025-06-17 15:21:36 +08:00

f5_tts/model

Fix bugs in install.sh, reduce log noise, and improve error reporting (#2464)

2025-06-17 15:21:36 +08:00

feature_extractor

Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

2025-04-07 16:42:47 +08:00

module

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

prepare_datasets

Fix bugs in install.sh, reduce log noise, and improve error reporting (#2464)

2025-06-17 15:21:36 +08:00

pretrained_models

Delete GPT_SoVITS/pretrained_models/init

2024-01-17 18:41:45 +08:00

text

Implement G2PW processing enhancements in TTS framework

2026-03-12 23:04:39 +08:00

TTS_infer_pack

Enhance TTS audio processing with improved resampling and profiling metrics

2026-03-13 16:45:00 +08:00

download.py

Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

2025-04-07 16:42:47 +08:00

export_torch_script_v3v4.py

Fix bugs in install.sh, reduce log noise, and improve error reporting (#2464)

2025-06-17 15:21:36 +08:00

export_torch_script.py

尝试 stream infer (#2469)

2025-11-28 21:36:57 +08:00

inference_cli.py

Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

2025-04-07 16:42:47 +08:00

inference_gui.py

Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

2025-04-07 16:42:47 +08:00

inference_webui_fast.py

对齐gpt topk默认采样参数 (#2696)

2025-12-19 16:05:36 +08:00

inference_webui.py

Update inference_webui.py

2025-07-10 18:16:24 +08:00

onnx_export.py

Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

2025-04-07 16:42:47 +08:00

process_ckpt.py

Fix bugs in install.sh, reduce log noise, and improve error reporting (#2464)

2025-06-17 15:21:36 +08:00

s1_train.py

Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

2025-04-07 16:42:47 +08:00

s2_train_v3_lora.py

Add files via upload

2025-11-28 22:02:03 +08:00

s2_train_v3.py

Add files via upload

2025-11-28 22:02:03 +08:00

s2_train.py

Add files via upload

2025-11-28 22:02:03 +08:00

stream_v2pro.py

尝试 stream infer (#2469)

2025-11-28 21:36:57 +08:00

sv.py

Fix bugs in install.sh, reduce log noise, and improve error reporting (#2464)

2025-06-17 15:21:36 +08:00

utils.py

Resolve Python Logger warnings (#2379)

2025-06-10 18:03:23 +08:00