SelVA: Hear What Matters! Text-conditioned Selective Video-to-Audio Generation

.
├── weights/
│   ├── video_enc_sup_5.pth # text-conditioned video encoder
│   └── generator_small_16k_sup_5.pth # v2a generator
└── ext_weights/
    ├── synchformer_state_dict.pth # pretrained Synchformer (24-01-04T16-39-21)
    ├── best_netG.pt # BigVGAN vocoder
    ├── v1-16.pth # vae 16kHz
    └── v1-44.pth # vae 44kHz