Add voice similarity control + improve reference audio processing

Upgrade audio quality: pro mixing chain, better inference params, htdemucs_ft

Fix GPU timeout: increase to 300s, lower default diffusion steps to 10

Add GPU worker debug logging to diagnose ZeroGPU import errors

Replace RVC with Seed-VC for zero-shot voice conversion

Implement real RVC v2 inference pipeline with HuBERT + FAISS + generator

Fix: monkey-patch gradio_client get_type for bool schema crash on Gradio 5.12.0

Import all @spaces.GPU functions at top level for ZeroGPU detection

Fix Gradio 5 compatibility: update gr.update() and let HF manage gradio version

Remove show_api=False which breaks Gradio 5 + ZeroGPU API detection

Upgrade to Gradio 5.12.0 for proper ZeroGPU authentication

Rewrite inference with fallback: try Applio, then pitch-shift + FAISS

Better error messages + reduce segments to 40 for GPU time limit

Restore full quality params now that GPU is available

Import @spaces.GPU functions at top level for ZeroGPU detection

Skip HiFi-GAN training on CPU, use pre-trained model + FAISS index

Optimize training for CPU: limit slices, reduce batch size and epochs

Pin starlette<0.38.0 to fix TemplateResponse API incompatibility

Patch jinja2 LRUCache to handle unhashable keys from gradio 4.44.0

Fix gradio 4.44.0 crash: catch TypeError instead of modifying schema dicts

Fix gradio 4.44.0 crashes: replace Dataframe with HTML + better patch

Monkey-patch gradio_client bug for additionalProperties bool

Fix gradio crash: add show_api=False and pin gradio_client 1.3.0

Fix gradio compatibility: upgrade to 4.44.1+ and set server_name

Initial commit: Clone Vocal RVC - web voice cloning tool