├── GPT_VAE_train.py ├── GPT_train.py ├── MSGVenv.yml ├── README.md ├── callbacks ├── GPT_VAE_callbacks.py ├── GPT_callbacks.py └── VAE_callbacks.py ├── config ├── config_GPT_VAE_vas.py ├── config_GPT_VAE_vggsound.py ├── config_GPT_vas.py └── config_vas.py ├── data ├── available_clips.txt ├── download_vas_features.sh ├── download_vggsound_features.sh ├── md5sum_vggsound.md5 ├── train_means_stds_melspec_10s_22050hz.txt ├── vas_train.txt ├── vas_valid.txt ├── vggsound.csv ├── vggsound_test.txt ├── vggsound_train.txt └── vggsound_valid.txt ├── datasets ├── datamodule.py ├── transforms.py ├── vas.py └── vggsound.py ├── feature_extraction ├── demo_utils.py ├── extract_codes.py └── extract_mel_spectrogram.py ├── gpu_processes.txt ├── modules ├── Lit_vae.py ├── __init__.py ├── decoders │ ├── __init__.py │ ├── dec_lstm.py │ ├── decoder.py │ ├── decoder_help.py │ └── decoder_helper.py ├── discriminators │ ├── __init__.py │ └── discriminator_linear.py ├── encoders │ ├── __init__.py │ ├── enc_lstm.py │ ├── encoder.py │ └── gaussian_encoder.py ├── lm │ ├── __init__.py │ └── lm_lstm.py ├── utils.py └── vae.py ├── requirements.txt ├── transformer ├── Lit_GPT_VAE.py ├── __init__.py ├── decoders.py ├── encoders.py ├── minGPT.py └── utils.py ├── utils.py ├── vocoder ├── logs │ └── vggsound │ │ ├── args.yml │ │ └── best_netG.pt └── modules.py └── vqvae └── big_model_attn_gan.py /GPT_VAE_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/GPT_VAE_train.py -------------------------------------------------------------------------------- /GPT_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/GPT_train.py -------------------------------------------------------------------------------- /MSGVenv.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/MSGVenv.yml -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/README.md -------------------------------------------------------------------------------- /callbacks/GPT_VAE_callbacks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/callbacks/GPT_VAE_callbacks.py -------------------------------------------------------------------------------- /callbacks/GPT_callbacks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/callbacks/GPT_callbacks.py -------------------------------------------------------------------------------- /callbacks/VAE_callbacks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/callbacks/VAE_callbacks.py -------------------------------------------------------------------------------- /config/config_GPT_VAE_vas.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/config/config_GPT_VAE_vas.py -------------------------------------------------------------------------------- /config/config_GPT_VAE_vggsound.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/config/config_GPT_VAE_vggsound.py -------------------------------------------------------------------------------- /config/config_GPT_vas.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/config/config_GPT_vas.py -------------------------------------------------------------------------------- /config/config_vas.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/config/config_vas.py -------------------------------------------------------------------------------- /data/available_clips.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/data/available_clips.txt -------------------------------------------------------------------------------- /data/download_vas_features.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/data/download_vas_features.sh -------------------------------------------------------------------------------- /data/download_vggsound_features.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/data/download_vggsound_features.sh -------------------------------------------------------------------------------- /data/md5sum_vggsound.md5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/data/md5sum_vggsound.md5 -------------------------------------------------------------------------------- /data/train_means_stds_melspec_10s_22050hz.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/data/train_means_stds_melspec_10s_22050hz.txt -------------------------------------------------------------------------------- /data/vas_train.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/data/vas_train.txt -------------------------------------------------------------------------------- /data/vas_valid.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/data/vas_valid.txt -------------------------------------------------------------------------------- /data/vggsound.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/data/vggsound.csv -------------------------------------------------------------------------------- /data/vggsound_test.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/data/vggsound_test.txt -------------------------------------------------------------------------------- /data/vggsound_train.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/data/vggsound_train.txt -------------------------------------------------------------------------------- /data/vggsound_valid.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/data/vggsound_valid.txt -------------------------------------------------------------------------------- /datasets/datamodule.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/datasets/datamodule.py -------------------------------------------------------------------------------- /datasets/transforms.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/datasets/transforms.py -------------------------------------------------------------------------------- /datasets/vas.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/datasets/vas.py -------------------------------------------------------------------------------- /datasets/vggsound.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/datasets/vggsound.py -------------------------------------------------------------------------------- /feature_extraction/demo_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/feature_extraction/demo_utils.py -------------------------------------------------------------------------------- /feature_extraction/extract_codes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/feature_extraction/extract_codes.py -------------------------------------------------------------------------------- /feature_extraction/extract_mel_spectrogram.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/feature_extraction/extract_mel_spectrogram.py -------------------------------------------------------------------------------- /gpu_processes.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/gpu_processes.txt -------------------------------------------------------------------------------- /modules/Lit_vae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/modules/Lit_vae.py -------------------------------------------------------------------------------- /modules/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/modules/__init__.py -------------------------------------------------------------------------------- /modules/decoders/__init__.py: -------------------------------------------------------------------------------- 1 | from .dec_lstm import * 2 | -------------------------------------------------------------------------------- /modules/decoders/dec_lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/modules/decoders/dec_lstm.py -------------------------------------------------------------------------------- /modules/decoders/decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/modules/decoders/decoder.py -------------------------------------------------------------------------------- /modules/decoders/decoder_help.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/modules/decoders/decoder_help.py -------------------------------------------------------------------------------- /modules/decoders/decoder_helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/modules/decoders/decoder_helper.py -------------------------------------------------------------------------------- /modules/discriminators/__init__.py: -------------------------------------------------------------------------------- 1 | from .discriminator_linear import * -------------------------------------------------------------------------------- /modules/discriminators/discriminator_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/modules/discriminators/discriminator_linear.py -------------------------------------------------------------------------------- /modules/encoders/__init__.py: -------------------------------------------------------------------------------- 1 | from .enc_lstm import * 2 | -------------------------------------------------------------------------------- /modules/encoders/enc_lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/modules/encoders/enc_lstm.py -------------------------------------------------------------------------------- /modules/encoders/encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/modules/encoders/encoder.py -------------------------------------------------------------------------------- /modules/encoders/gaussian_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/modules/encoders/gaussian_encoder.py -------------------------------------------------------------------------------- /modules/lm/__init__.py: -------------------------------------------------------------------------------- 1 | from .lm_lstm import * -------------------------------------------------------------------------------- /modules/lm/lm_lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/modules/lm/lm_lstm.py -------------------------------------------------------------------------------- /modules/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/modules/utils.py -------------------------------------------------------------------------------- /modules/vae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/modules/vae.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/requirements.txt -------------------------------------------------------------------------------- /transformer/Lit_GPT_VAE.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/transformer/Lit_GPT_VAE.py -------------------------------------------------------------------------------- /transformer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/transformer/__init__.py -------------------------------------------------------------------------------- /transformer/decoders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/transformer/decoders.py -------------------------------------------------------------------------------- /transformer/encoders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/transformer/encoders.py -------------------------------------------------------------------------------- /transformer/minGPT.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/transformer/minGPT.py -------------------------------------------------------------------------------- /transformer/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/transformer/utils.py -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/utils.py -------------------------------------------------------------------------------- /vocoder/logs/vggsound/args.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/vocoder/logs/vggsound/args.yml -------------------------------------------------------------------------------- /vocoder/logs/vggsound/best_netG.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/vocoder/logs/vggsound/best_netG.pt -------------------------------------------------------------------------------- /vocoder/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/vocoder/modules.py -------------------------------------------------------------------------------- /vqvae/big_model_attn_gan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/karchkha/MelSpec_GPT_VQVAE/HEAD/vqvae/big_model_attn_gan.py --------------------------------------------------------------------------------