2025-06-02T13:27:45.781379288Z ==========
2025-06-02T13:27:45.781397771Z == CUDA ==
2025-06-02T13:27:45.781440246Z ==========
2025-06-02T13:27:45.784022431Z CUDA Version 12.8.1
2025-06-02T13:27:45.784870259Z Container image Copyright (c) 2016-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2025-06-02T13:27:45.785529804Z This container image and its contents are governed by the NVIDIA Deep Learning Container License.
2025-06-02T13:27:45.785533538Z By pulling and using the container, you accept the terms and conditions of this license:
2025-06-02T13:27:45.785536889Z https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license
2025-06-02T13:27:45.785541414Z A copy of this license is made available in this container at /NGC-DL-CONTAINER-LICENSE for your convenience.
2025-06-02T13:27:54.437498057Z 2025-06-02 13:27:54 [INFO] __main__: Starting TTS Server directly on http://0.0.0.0:8004
2025-06-02T13:27:54.437527911Z 2025-06-02 13:27:54 [INFO] __main__: API documentation will be available at http://0.0.0.0:8004/docs
2025-06-02T13:27:54.437530968Z 2025-06-02 13:27:54 [INFO] __main__: Web UI will be available at http://0.0.0.0:8004/
2025-06-02T13:27:54.488106304Z INFO:     Started server process [31]
2025-06-02T13:27:54.488137785Z INFO:     Waiting for application startup.
2025-06-02T13:27:54.488286719Z 2025-06-02 13:27:54 [INFO] server: TTS Server: Initializing application...
2025-06-02T13:27:54.488394403Z 2025-06-02 13:27:54 [INFO] server: Configuration loaded. Log file at: /app/logs\tts_server.log
2025-06-02T13:27:54.488627199Z 2025-06-02 13:27:54 [INFO] engine: Attempting to load TTS model on device: cuda
2025-06-02T13:27:54.488680044Z 2025-06-02 13:27:54 [INFO] engine: Attempting to load model directly using from_pretrained (expected from Hugging Face repository: ResembleAI/chatterbox or library default).
2025-06-02T13:28:09.694745397Z /usr/local/lib/python3.10/dist-packages/diffusers/models/lora.py:393: FutureWarning: `LoRACompatibleLinear` is deprecated and will be removed in version 1.0.0. Use of `LoRACompatibleLinear` is deprecated. Please switch to PEFT backend by installing PEFT: `pip install peft`.
2025-06-02T13:28:09.694781621Z   deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message)
2025-06-02T13:28:10.986816084Z 2025-06-02 13:28:10 [INFO] root: input frame rate=25
2025-06-02T13:28:13.222766533Z loaded PerthNet (Implicit) at step 250,000
2025-06-02T13:28:13.224442327Z 2025-06-02 13:28:13 [INFO] engine: Successfully loaded TTS model using from_pretrained (expected from 'ResembleAI/chatterbox' or library default).
2025-06-02T13:28:13.224573603Z 2025-06-02 13:28:13 [INFO] engine: TTS Model loaded successfully. Engine sample rate: 24000 Hz.
2025-06-02T13:28:13.224578173Z 2025-06-02 13:28:13 [INFO] server: TTS Model loaded successfully via engine.
2025-06-02T13:28:13.225131059Z 2025-06-02 13:28:13 [INFO] server: Application startup sequence complete.
2025-06-02T13:28:13.225288638Z INFO:     Application startup complete.
2025-06-02T13:28:13.225900212Z INFO:     Uvicorn running on http://0.0.0.0:8004 (Press CTRL+C to quit)
2025-06-02T13:28:14.727357250Z 2025-06-02 13:28:14 [INFO] server: Attempting to open web browser to: http://localhost:8004/