Align Higgs app with current ZeroGPU runtime

Test ZeroGPU large allocation

Convert Space to Higgs Audio v3 only

Auto-transcribe selected voice with CPU-only Whisper to pre-fill the Higgs reference transcript

Add Higgs Audio v3 (4B) as a selectable voice backend alongside DramaBox

Fix HF Space metadata

Merge HF Space init

Initial DramaBox TTS space

initial commit