Spaces:
Running
Running
| { | |
| "base_config": "config/vocoder.json", | |
| "model_type": "GANVocoder", | |
| // TODO: Choose your needed datasets | |
| "dataset": [ | |
| "csd", | |
| "kising", | |
| "m4singer", | |
| "nus48e", | |
| "opencpop", | |
| "opensinger", | |
| "opera", | |
| "pjs", | |
| "popbutfy", | |
| "popcs", | |
| "ljspeech", | |
| "vctk", | |
| "libritts", | |
| ], | |
| "dataset_path": { | |
| // TODO: Fill in your dataset path | |
| "csd": "[dataset path]", | |
| "kising": "[dataset path]", | |
| "m4singer": "[dataset path]", | |
| "nus48e": "[dataset path]", | |
| "opencpop": "[dataset path]", | |
| "opensinger": "[dataset path]", | |
| "opera": "[dataset path]", | |
| "pjs": "[dataset path]", | |
| "popbutfy": "[dataset path]", | |
| "popcs": "[dataset path]", | |
| "ljspeech": "[dataset path]", | |
| "vctk": "[dataset path]", | |
| "libritts": "[dataset path]", | |
| }, | |
| // TODO: Fill in the output log path | |
| "log_dir": "ckpts/vocoder", | |
| "preprocess": { | |
| // Acoustic features | |
| "extract_mel": true, | |
| "extract_audio": true, | |
| "extract_pitch": false, | |
| "extract_uv": false, | |
| "pitch_extractor": "parselmouth", | |
| // Features used for model training | |
| "use_mel": true, | |
| "use_frame_pitch": false, | |
| "use_uv": false, | |
| "use_audio": true, | |
| // TODO: Fill in the output data path | |
| "processed_dir": "data/", | |
| "n_mel": 100, | |
| "sample_rate": 24000 | |
| }, | |
| "model": { | |
| // TODO: Choose your needed discriminators | |
| "discriminators": [ | |
| "msd", | |
| "mpd", | |
| "msstftd", | |
| "mssbcqtd", | |
| ], | |
| "mpd": { | |
| "mpd_reshapes": [ | |
| 2, | |
| 3, | |
| 5, | |
| 7, | |
| 11 | |
| ], | |
| "use_spectral_norm": false, | |
| "discriminator_channel_mult_factor": 1 | |
| }, | |
| "mrd": { | |
| "resolutions": [[1024, 120, 600], [2048, 240, 1200], [512, 50, 240]], | |
| "use_spectral_norm": false, | |
| "discriminator_channel_mult_factor": 1, | |
| "mrd_override": false | |
| }, | |
| "msstftd": { | |
| "filters": 32 | |
| }, | |
| "mssbcqtd": { | |
| hop_lengths: [512, 256, 256], | |
| filters: 32, | |
| max_filters: 1024, | |
| filters_scale: 1, | |
| dilations: [1, 2, 4], | |
| in_channels: 1, | |
| out_channels: 1, | |
| n_octaves: [9, 9, 9], | |
| bins_per_octaves: [24, 36, 48] | |
| }, | |
| }, | |
| "train": { | |
| // TODO: Choose a suitable batch size, training epoch, and save stride | |
| "batch_size": 32, | |
| "max_epoch": 1000000, | |
| "save_checkpoint_stride": [20], | |
| "adamw": { | |
| "lr": 2.0e-4, | |
| "adam_b1": 0.8, | |
| "adam_b2": 0.99 | |
| }, | |
| "exponential_lr": { | |
| "lr_decay": 0.999 | |
| }, | |
| } | |
| } |