| model: | |
| base_learning_rate: 1.0e-06 | |
| target: specvqgan.models.vqgan.VQModel | |
| params: | |
| embed_dim: 256 | |
| n_embed: 256 | |
| ddconfig: | |
| double_z: false | |
| z_channels: 256 | |
| resolution: 848 | |
| in_channels: 1 | |
| out_ch: 1 | |
| ch: 128 | |
| ch_mult: | |
| - 1 | |
| - 1 | |
| - 2 | |
| - 2 | |
| - 4 | |
| num_res_blocks: 2 | |
| attn_resolutions: | |
| - 53 | |
| dropout: 0.0 | |
| lossconfig: | |
| target: specvqgan.modules.losses.vqperceptual.VQLPAPSWithDiscriminator_without_per | |
| params: | |
| disc_conditional: false | |
| disc_in_channels: 1 | |
| disc_start: 50001 | |
| disc_weight: 0.8 | |
| codebook_weight: 1.0 | |
| min_adapt_weight: 1.0 | |
| max_adapt_weight: 1.0 | |
| perceptual_weight: 0.0 | |
| data: | |
| target: train.SpectrogramDataModuleFromConfig | |
| params: | |
| batch_size: 12 | |
| num_workers: 8 | |
| spec_dir_path: /apdcephfs_cq2/share_1297902/speech_user/shaunxliu/dongchao/code/VQ-VAE/audioset_pre | |
| sample_rate: 22050 | |
| mel_num: 80 | |
| spec_len: 860 | |
| spec_crop_len: 848 | |
| random_crop: false | |
| train: | |
| target: specvqgan.data.AllAudio.VASSpecsTrain | |
| params: | |
| specs_dataset_cfg: | |
| split_path: /apdcephfs_cq2/share_1297902/speech_user/shaunxliu/dongchao/code/VQ-VAE/audioset_pre | |
| validation: | |
| target: specvqgan.data.AllAudio.VASSpecsValidation | |
| params: | |
| specs_dataset_cfg: | |
| split_path: /apdcephfs_cq2/share_1297902/speech_user/shaunxliu/dongchao/code/VQ-VAE/audioset_pre | |