Makinde d00e28ffda Fix: Prevent crashes when HuggingFace is unreachable ...

Implements offline mode patch for API stability issues:

- Add hf_offline_patch.py to monkey-patch huggingface_hub
- Force cache-only lookups before mlx_audio imports
- Create symlink from original Qwen repo to MLX community version
  when only MLX version is cached

This fixes:
- Issue #150: Internet required even with cached models
- Issue #151: API crashes when HF network fails

The patch ensures that if models are locally cached, no network
requests are made to HuggingFace during speech generation.

2026-02-22 01:57:02 -08:00

..

__init__.py

Enhance MLX and PyTorch Backend Integration

2026-01-29 23:11:48 -08:00

mlx_backend.py

Fix: Prevent crashes when HuggingFace is unreachable

2026-02-22 01:57:02 -08:00

pytorch_backend.py

fix: resolve multiple issues (#96, #119, #111, #108, #121, #125, #127)

2026-02-20 23:23:38 +05:30