Spaces:
Running
on
Zero
Running
on
Zero
File size: 7,074 Bytes
45ee559 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 |
{
"run_name": "multiband-melgan",
"run_description": "multiband melgan mean-var scaling",
// AUDIO PARAMETERS
"audio":{
"fft_size": 1024, // number of stft frequency levels. Size of the linear spectogram frame.
"win_length": 1024, // stft window length in ms.
"hop_length": 256, // stft window hop-lengh in ms.
"frame_length_ms": null, // stft window length in ms.If null, 'win_length' is used.
"frame_shift_ms": null, // stft window hop-lengh in ms. If null, 'hop_length' is used.
// Audio processing parameters
"sample_rate": 22050, // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled.
"preemphasis": 0.0, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis.
"ref_level_db": 20, // reference level db, theoretically 20db is the sound of air.
"log_func": "np.log10",
"do_sound_norm": true,
// Silence trimming
"do_trim_silence": false,// enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true)
"trim_db": 60, // threshold for timming silence. Set this according to your dataset.
// MelSpectrogram parameters
"num_mels": 80, // size of the mel spec frame.
"mel_fmin": 50.0, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
"mel_fmax": 7600.0, // maximum freq level for mel-spec. Tune for dataset!!
"spec_gain": 1.0, // scaler value appplied after log transform of spectrogram.
// Normalization parameters
"signal_norm": true, // normalize spec values. Mean-Var normalization if 'stats_path' is defined otherwise range normalization defined by the other params.
"min_level_db": -100, // lower bound for normalization
"symmetric_norm": true, // move normalization to range [-1, 1]
"max_norm": 4.0, // scale normalization to range [-max_norm, max_norm] or [0, max_norm]
"clip_norm": true, // clip normalized values into the range.
"stats_path": null
},
// DISTRIBUTED TRAINING
// "distributed":{
// "backend": "nccl",
// "url": "tcp:\/\/localhost:54321"
// },
// MODEL PARAMETERS
"use_pqmf": true,
// LOSS PARAMETERS
"use_stft_loss": true,
"use_subband_stft_loss": true,
"use_mse_gan_loss": true,
"use_hinge_gan_loss": false,
"use_feat_match_loss": false, // use only with melgan discriminators
"use_l1_spec_loss": true,
// loss weights
"stft_loss_weight": 0.5,
"subband_stft_loss_weight": 0.5,
"mse_G_loss_weight": 2.5,
"hinge_G_loss_weight": 2.5,
"feat_match_loss_weight": 25,
"l1_spec_loss_weight": 2.5,
// multiscale stft loss parameters
"stft_loss_params": {
"n_ffts": [1024, 2048, 512],
"hop_lengths": [120, 240, 50],
"win_lengths": [600, 1200, 240]
},
// subband multiscale stft loss parameters
"subband_stft_loss_params":{
"n_ffts": [384, 683, 171],
"hop_lengths": [30, 60, 10],
"win_lengths": [150, 300, 60]
},
"l1_spec_loss_params": {
"use_mel": true,
"sample_rate": 22050,
"n_fft": 1024,
"hop_length": 256,
"win_length": 1024,
"n_mels": 80,
"mel_fmin": 0.0,
"mel_fmax": null
},
"target_loss": "G_avg_loss", // loss value to pick the best model to save after each epoch
// DISCRIMINATOR
"discriminator_model": "melgan_multiscale_discriminator",
"discriminator_model_params":{
"base_channels": 16,
"max_channels":512,
"downsample_factors":[4, 4, 4]
},
"steps_to_start_discriminator": 200000, // steps required to start GAN trainining.1
// GENERATOR
"generator_model": "multiband_melgan_generator",
"generator_model_params": {
"upsample_factors":[8, 4, 2],
"num_res_blocks": 4
},
// DATASET
"data_path": "tests/data/ljspeech/wavs/",
"feature_path": null,
"seq_len": 16384,
"pad_short": 2000,
"conv_pad": 0,
"use_noise_augment": false,
"use_cache": true,
"reinit_layers": [], // give a list of layer names to restore from the given checkpoint. If not defined, it reloads all heuristically matching layers.
// TRAINING
"batch_size": 4, // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'.
// VALIDATION
"run_eval": true,
"test_delay_epochs": 10, //Until attention is aligned, testing only wastes computation time.
"test_sentences_file": null, // set a file to load sentences to be used for testing. If it is null then we use default english sentences.
// OPTIMIZER
"epochs": 1, // total number of epochs to train.
"wd": 0.0, // Weight decay weight.
"gen_clip_grad": -1, // Generator gradient clipping threshold. Apply gradient clipping if > 0
"disc_clip_grad": -1, // Discriminator gradient clipping threshold.
"optimizer": "AdamW",
"optimizer_params":{
"betas": [0.8, 0.99],
"weight_decay": 0.0
},
"lr_scheduler_gen": "MultiStepLR", // one of the schedulers from https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
"lr_scheduler_gen_params": {
"gamma": 0.5,
"milestones": [100000, 200000, 300000, 400000, 500000, 600000]
},
"lr_scheduler_disc": "MultiStepLR", // one of the schedulers from https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
"lr_scheduler_disc_params": {
"gamma": 0.5,
"milestones": [100000, 200000, 300000, 400000, 500000, 600000]
},
"lr_gen": 1e-4, // Initial learning rate. If Noam decay is active, maximum learning rate.
"lr_disc": 1e-4,
// TENSORBOARD and LOGGING
"print_step": 1, // Number of steps to log traning on console.
"print_eval": false, // If True, it prints loss values for each step in eval run.
"save_step": 25000, // Number of training steps expected to plot training stats on TB and save model checkpoints.
"checkpoint": true, // If true, it saves checkpoints per "save_step"
"keep_all_best": true, // If true, keeps all best_models after keep_after steps
"keep_after": 10000, // Global step after which to keep best models if keep_all_best is true
"tb_model_param_stats": false, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
// DATA LOADING
"num_loader_workers": 0, // number of training data loader processes. Don't set it too big. 4-8 are good values.
"num_eval_loader_workers": 0, // number of evaluation data loader processes.
"eval_split_size": 10,
// PATHS
"output_path": "tests/train_outputs/"
}
|