├── .gitignore ├── LICENSE ├── README.md ├── assets ├── Algorithm.png ├── case_audio.png └── case_image.png ├── configs ├── imagenet_simvq_128_B.yaml └── libritts_24khz.yaml ├── evaluation.py ├── evaluation_speech.py ├── generate_manifest.py ├── main.py ├── metrics ├── UTMOS.py ├── fid.py ├── inception.py └── periodicity.py ├── requirements.txt ├── requirements_audio.txt └── taming ├── data ├── base.py ├── helper_types.py ├── imagenet.py ├── libritts.py └── utils.py ├── models ├── vq.py └── vq_audio.py ├── modules ├── autoencoder │ └── lpips │ │ └── vgg.pth ├── diffusionmodules │ ├── conv.py │ ├── fourierhead.py │ ├── improved_model.py │ ├── model.py │ ├── seanet.py │ └── vocosbackbone.py ├── discriminator │ ├── base.py │ ├── dac.py │ ├── model.py │ └── mpmr.py ├── ema.py ├── losses │ ├── __init__.py │ ├── lpips.py │ ├── speech_loss.py │ ├── stft.py │ └── vqperceptual.py ├── scheduler │ └── lr_scheduler.py ├── util.py └── vqvae │ ├── distrib.py │ └── quantize.py └── util.py /.gitignore: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/README.md -------------------------------------------------------------------------------- /assets/Algorithm.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/assets/Algorithm.png -------------------------------------------------------------------------------- /assets/case_audio.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/assets/case_audio.png -------------------------------------------------------------------------------- /assets/case_image.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/assets/case_image.png -------------------------------------------------------------------------------- /configs/imagenet_simvq_128_B.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/configs/imagenet_simvq_128_B.yaml -------------------------------------------------------------------------------- /configs/libritts_24khz.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/configs/libritts_24khz.yaml -------------------------------------------------------------------------------- /evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/evaluation.py -------------------------------------------------------------------------------- /evaluation_speech.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/evaluation_speech.py -------------------------------------------------------------------------------- /generate_manifest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/generate_manifest.py -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/main.py -------------------------------------------------------------------------------- /metrics/UTMOS.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/metrics/UTMOS.py -------------------------------------------------------------------------------- /metrics/fid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/metrics/fid.py -------------------------------------------------------------------------------- /metrics/inception.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/metrics/inception.py -------------------------------------------------------------------------------- /metrics/periodicity.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/metrics/periodicity.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/requirements.txt -------------------------------------------------------------------------------- /requirements_audio.txt: -------------------------------------------------------------------------------- 1 | fairseq 2 | torchcrepe 3 | pesq 4 | pystoi -------------------------------------------------------------------------------- /taming/data/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/data/base.py -------------------------------------------------------------------------------- /taming/data/helper_types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/data/helper_types.py -------------------------------------------------------------------------------- /taming/data/imagenet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/data/imagenet.py -------------------------------------------------------------------------------- /taming/data/libritts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/data/libritts.py -------------------------------------------------------------------------------- /taming/data/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/data/utils.py -------------------------------------------------------------------------------- /taming/models/vq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/models/vq.py -------------------------------------------------------------------------------- /taming/models/vq_audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/models/vq_audio.py -------------------------------------------------------------------------------- /taming/modules/autoencoder/lpips/vgg.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/autoencoder/lpips/vgg.pth -------------------------------------------------------------------------------- /taming/modules/diffusionmodules/conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/diffusionmodules/conv.py -------------------------------------------------------------------------------- /taming/modules/diffusionmodules/fourierhead.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/diffusionmodules/fourierhead.py -------------------------------------------------------------------------------- /taming/modules/diffusionmodules/improved_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/diffusionmodules/improved_model.py -------------------------------------------------------------------------------- /taming/modules/diffusionmodules/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/diffusionmodules/model.py -------------------------------------------------------------------------------- /taming/modules/diffusionmodules/seanet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/diffusionmodules/seanet.py -------------------------------------------------------------------------------- /taming/modules/diffusionmodules/vocosbackbone.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/diffusionmodules/vocosbackbone.py -------------------------------------------------------------------------------- /taming/modules/discriminator/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/discriminator/base.py -------------------------------------------------------------------------------- /taming/modules/discriminator/dac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/discriminator/dac.py -------------------------------------------------------------------------------- /taming/modules/discriminator/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/discriminator/model.py -------------------------------------------------------------------------------- /taming/modules/discriminator/mpmr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/discriminator/mpmr.py -------------------------------------------------------------------------------- /taming/modules/ema.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/ema.py -------------------------------------------------------------------------------- /taming/modules/losses/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/losses/__init__.py -------------------------------------------------------------------------------- /taming/modules/losses/lpips.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/losses/lpips.py -------------------------------------------------------------------------------- /taming/modules/losses/speech_loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/losses/speech_loss.py -------------------------------------------------------------------------------- /taming/modules/losses/stft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/losses/stft.py -------------------------------------------------------------------------------- /taming/modules/losses/vqperceptual.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/losses/vqperceptual.py -------------------------------------------------------------------------------- /taming/modules/scheduler/lr_scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/scheduler/lr_scheduler.py -------------------------------------------------------------------------------- /taming/modules/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/util.py -------------------------------------------------------------------------------- /taming/modules/vqvae/distrib.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/vqvae/distrib.py -------------------------------------------------------------------------------- /taming/modules/vqvae/quantize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/modules/vqvae/quantize.py -------------------------------------------------------------------------------- /taming/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/youngsheen/SimVQ/HEAD/taming/util.py --------------------------------------------------------------------------------