Swallow ZeroGPU low-level CUDA init guard in torch.cuda.set_device (speechbrain calls it unconditionally at init)

Bump speechbrain to 1.x (0.5.x branch never fixed use_auth_token)

Add torchvision back (not preinstalled on ZeroGPU; upstream code imports it)

Bump speechbrain to last 0.5.x (use_auth_token removed in huggingface_hub)

Adapt to ZeroGPU: refactor read into @spaces.GPU closure; drop torch/torchvision pins

Update requirements.txt

Update README.md

overwrite some pitch values at the start and end to make it sound more lively

Update Preprocessing/TextFrontend.py

Update app.py

Update Modules/ControllabilityGAN/GAN.py

Update Modules/ControllabilityGAN/GAN.py

Update Modules/ControllabilityGAN/GAN.py

Update InferenceInterfaces/ToucanTTSInterface.py

Update InferenceInterfaces/ToucanTTSInterface.py

Update app.py

Update Modules/ControllabilityGAN/GAN.py

Update Modules/ControllabilityGAN/wgan/resnet_1.py

Update Modules/ControllabilityGAN/wgan/wgan_qc.py

Update InferenceInterfaces/ControllableInterface.py

Update requirements.txt

Update requirements.txt

Update app.py

Update README.md

Update app.py

Update README.md

Update app.py

Update app.py

change default loudness

make the audio a bit quieter by default

Update app.py

Update README.md

Update Modules/ControllabilityGAN/GAN.py

Update InferenceInterfaces/ControllableInterface.py

Update app.py

Upload best.pt

update vocoder to newest version

Delete best.pt

Update InferenceInterfaces/ToucanTTSInterface.py

Upload best.pt

Delete Models/Vocoder/best.pt

Update Modules/Vocoder/HiFiGAN_Generator.py

Delete Models/audioseal/generator.pth

Upload best.pt

update to the current version

Merge remote-tracking branch 'origin/main'

Update app.py

Update app.py

Update InferenceInterfaces/ControllableInterface.py

Update app.py