Spaces:
Paused
Paused
| gradio==5.35.0 | |
| transformers | |
| torch | |
| accelerate | |
| bitsandbytes | |
| soundfile | |
| numpy | |
| librosa | |
| # LFM2.5-Audio end-to-end model | |
| liquid-audio | |
| # Qwen3-TTS (voice cloning + stock voice for narration) | |
| qwen-tts>=0.1.1 | |
| huggingface-hub>=0.23.0 | |
| # FlashAttention-2: not in requirements (needs CUDA at build time). | |
| # Code auto-falls back to eager/SDPA if unavailable. | |
| # To enable: pip install flash-attn --no-build-isolation (at runtime) | |