Hello, I am trying to get local TTS to work, I done a full clean install of Miniconda and the new Chatterbox. when I lunch Chatterbox, it look like it all working, but I get no sound, I use CPU GUP and Chatterbox. option none work.
I do get sound for YouTube and in one of my test the ai played a video and that had sound.
Can anyone help, I out of idea
Thank you
Chatterbox output
(chatterbox) PS C:\local-TTS-Chatterbox-main> python -m uvicorn server:app --host 0.0.0.0 --port 3200
Patching perth: using DummyWatermarker (no ARM binary available)
GPU: NVIDIA GeForce RTX 4090
CUDA Version: 12.4
Device: cuda
INFO: Started server process [22312]
INFO: Waiting for application startup.
Pre-loading turbo model...
Fetching 10 files: 100%|███████████████████████████████████████████████████████████████████████████| 10/10 [00:00<?, ?it/s]
C:\Users***.conda\envs\chatterbox\Lib\site-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.
deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message)
Loaded Chatterbox turbo model on cuda (9.3s)
- LSTM flatten_parameters
- HiFiGAN weight_norm removed (82 layers)
INFO: Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:3200 (Press CTRL+C to quit)