Add static_sox to requirements.txt

Fix Gradio Progress IndexError by using is not None

Fix noisereduce, UI progress, remove spaces.GPU for L4, and add train_cli.py

Fix Python 3.12 syntax: remove 'type' keyword for compatibility with 3.10

Fix Python 3.10 compatibility: add StrEnum fallback

Optimize RVC training: resumable training with checkpoints every 10 epochs and advanced UI options

Fix RVC training module structure and imports

Add __init__.py files and fix sys.path for rvc_logic

Fix IndentationError: properly rewrite rvc_logic files and cleanup binaries

Fix build error: use local rvc_logic (cleaned)

Delete old RVC folder

Migrate RVC training to ultimate-rvc library (no fairseq needed)

Fix build error: remove pinned torch and clean requirements

Integrate RVC training tab (100 epochs)

Remove redundant refresh button in Perfil tab as requested

Fix NameError by moving events to bottom of Blocks

UI: move refresh button out of accordion and fix sync between tabs

Resolve merge conflict: combine GPU optimization with Spanish UI and refresh button

Add refresh button and GPU optimization for original repo

fix: explicit float32 conversion and nan_to_num for audio data to fix 0:00 playback; restore allowed_paths

feat: add robust logging and diagnostics for ZeroGPU troubleshooting; fix '0 seconds' issue with explicit checks

fix: return actual audio data (numpy) from ZeroGPU function instead of file paths to ensure Gradio receives the content before the worker environment is destroyed

fix: move all output and storage directories from /tmp to local app subdirectories to fix Gradio serving issues on HF; explicitly allow results/checkpoints paths; set Audio type to filepath

fix: lazy-import torch/torchaudio in inference.py to avoid libcudart.so.13 crash; pin cu124 wheels in requirements to prevent demucs pulling CUDA-13 torchaudio

fix: consolidate Demucs+SeedVC+Mix into single @spaces.GPU function to fix ZeroGPU nested GPU call error; expose _separate_audio_impl; add libsox-dev to packages.txt

HF adaptation: fix ZeroGPU requirements, launch(), README metadata + hardware:zero-gpu

fix: add gradio==5.12.0 to requirements, fix de-esser bug (LowShelf->HighShelf), show_error=True

Update app.py

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

Fix inference tensor backward error: add torch.no_grad + inference_mode

Fix BigVGAN _from_pretrained compatibility with newer huggingface_hub

Add GPU worker debug logging to diagnose ZeroGPU import errors

Fix missing 'munch' dep + add detailed error wrapper for ZeroGPU

Bundle Seed-VC modules directly in repo for ZeroGPU compatibility

Fix ModuleNotFoundError: clone Seed-VC to app dir instead of /tmp

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

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

Convert pretrained checkpoint to RVC inference format for proper voice conversion

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

Remove @spaces.GPU from separation and inference for CPU fallback

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

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

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

Restore full quality params now that GPU is available