mirror of https://github.com/coqui-ai/TTS.git
remove *.json vocoder configs
Eren Gölge
parent
78b3825d0b
commit
6f4eed94f5
|
|
@ -1,158 +0,0 @@
|
|||
{
|
||||
"run_name": "multiband-melgan-rwd",
|
||||
"run_description": "multiband melgan with random window discriminator from https://arxiv.org/pdf/1909.11646.pdf",
|
||||
|
||||
// AUDIO PARAMETERS
|
||||
"audio":{
|
||||
// stft parameters
|
||||
"num_freq": 513, // 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.
|
||||
|
||||
// Silence trimming
|
||||
"do_trim_silence": true,// 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.
|
||||
|
||||
// Griffin-Lim
|
||||
"power": 1.5, // value to sharpen wav signals after GL algorithm.
|
||||
"griffin_lim_iters": 60,// #griffin-lim iterations. 30-60 is a good range. Larger the value, slower the generation.
|
||||
|
||||
// MelSpectrogram parameters
|
||||
"num_mels": 80, // size of the mel spec frame.
|
||||
"mel_fmin": 0.0, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
|
||||
"mel_fmax": 8000.0, // maximum freq level for mel-spec. Tune for dataset!!
|
||||
|
||||
// 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 // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored
|
||||
},
|
||||
|
||||
// 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
|
||||
|
||||
// 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,
|
||||
|
||||
// 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]
|
||||
},
|
||||
|
||||
"target_loss": "avg_G_loss", // loss value to pick the best model to save after each epoch
|
||||
|
||||
// DISCRIMINATOR
|
||||
"discriminator_model": "random_window_discriminator",
|
||||
"discriminator_model_params":{
|
||||
"uncond_disc_donwsample_factors": [8, 4],
|
||||
"cond_disc_downsample_factors": [[8, 4, 2, 2, 2], [8, 4, 2, 2], [8, 4, 2], [8, 4], [4, 2, 2]],
|
||||
"cond_disc_out_channels": [[128, 128, 256, 256], [128, 256, 256], [128, 256], [256], [128, 256]],
|
||||
"window_sizes": [512, 1024, 2048, 4096, 8192]
|
||||
},
|
||||
"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": "/home/erogol/Data/LJSpeech-1.1/wavs/",
|
||||
"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": 64, // 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
|
||||
"noam_schedule": false, // use noam warmup and lr schedule.
|
||||
"warmup_steps_gen": 4000, // Noam decay steps to increase the learning rate from 0 to "lr"
|
||||
"warmup_steps_disc": 4000,
|
||||
"epochs": 10000, // 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.
|
||||
"lr_gen": 0.0002, // Initial learning rate. If Noam decay is active, maximum learning rate.
|
||||
"lr_disc": 0.0002,
|
||||
"optimizer": "AdamW",
|
||||
"optimizer_params":{
|
||||
"betas": [0.8, 0.99],
|
||||
"weight_decay": 0.0
|
||||
},
|
||||
"lr_scheduler_gen": "ExponentialLR", // one of the schedulers from https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
|
||||
"lr_scheduler_gen_params": {
|
||||
"gamma": 0.999,
|
||||
"last_epoch": -1
|
||||
},
|
||||
"lr_scheduler_disc": "ExponentialLR", // one of the schedulers from https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
|
||||
"lr_scheduler_disc_params": {
|
||||
"gamma": 0.999,
|
||||
"last_epoch": -1
|
||||
},
|
||||
|
||||
// TENSORBOARD and LOGGING
|
||||
"print_step": 25, // 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": false, // 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": 4, // number of training data loader processes. Don't set it too big. 4-8 are good values.
|
||||
"num_val_loader_workers": 4, // number of evaluation data loader processes.
|
||||
"eval_split_size": 10,
|
||||
|
||||
// PATHS
|
||||
"output_path": "/home/erogol/Models/LJSpeech/"
|
||||
}
|
||||
|
||||
|
|
@ -1,148 +0,0 @@
|
|||
{
|
||||
"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": 0, // reference level db, theoretically 20db is the sound of air.
|
||||
|
||||
// Silence trimming
|
||||
"do_trim_silence": true,// 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": "/home/erogol/Data/LJSpeech-1.1/scale_stats.npy" // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored
|
||||
},
|
||||
|
||||
// DISTRIBUTED TRAINING
|
||||
// "distributed":{
|
||||
// "backend": "nccl",
|
||||
// "url": "tcp:\/\/localhost:54321"
|
||||
// },
|
||||
|
||||
// LOSS PARAMETERS
|
||||
"use_stft_loss": true,
|
||||
"use_subband_stft_loss": true, // use only with multi-band models.
|
||||
"use_mse_gan_loss": true,
|
||||
"use_hinge_gan_loss": false,
|
||||
"use_feat_match_loss": false, // use only with melgan discriminators
|
||||
|
||||
// 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,
|
||||
|
||||
// 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]
|
||||
},
|
||||
|
||||
"target_loss": "avg_G_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": "/home/erogol/Data/LJSpeech-1.1/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": 64, // 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": 10000, // 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.
|
||||
"lr_gen": 0.0002, // Initial learning rate. If Noam decay is active, maximum learning rate.
|
||||
"lr_disc": 0.0002,
|
||||
"optimizer": "AdamW",
|
||||
"optimizer_params":{
|
||||
"betas": [0.8, 0.99],
|
||||
"weight_decay": 0.0
|
||||
},
|
||||
"lr_scheduler_gen": "ExponentialLR", // one of the schedulers from https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
|
||||
"lr_scheduler_gen_params": {
|
||||
"gamma": 0.999,
|
||||
"last_epoch": -1
|
||||
},
|
||||
"lr_scheduler_disc": "ExponentialLR", // one of the schedulers from https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
|
||||
"lr_scheduler_disc_params": {
|
||||
"gamma": 0.999,
|
||||
"last_epoch": -1
|
||||
},
|
||||
|
||||
// TENSORBOARD and LOGGING
|
||||
"print_step": 25, // 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": false, // 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": 4, // number of training data loader processes. Don't set it too big. 4-8 are good values.
|
||||
"num_val_loader_workers": 4, // number of evaluation data loader processes.
|
||||
"eval_split_size": 10,
|
||||
|
||||
// PATHS
|
||||
"output_path": "/home/erogol/Models/LJSpeech/"
|
||||
}
|
||||
|
||||
|
|
@ -1,149 +0,0 @@
|
|||
{
|
||||
"run_name": "pwgan",
|
||||
"run_description": "parallel-wavegan training",
|
||||
|
||||
// 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": 0, // reference level db, theoretically 20db is the sound of air.
|
||||
|
||||
// Silence trimming
|
||||
"do_trim_silence": true,// 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": "/home/erogol/Data/LJSpeech-1.1/scale_stats.npy" // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored
|
||||
},
|
||||
|
||||
// DISTRIBUTED TRAINING
|
||||
// "distributed":{
|
||||
// "backend": "nccl",
|
||||
// "url": "tcp:\/\/localhost:54321"
|
||||
// },
|
||||
|
||||
// MODEL PARAMETERS
|
||||
"use_pqmf": true,
|
||||
|
||||
// LOSS PARAMETERS
|
||||
"use_stft_loss": true,
|
||||
"use_subband_stft_loss": false, // USE ONLY WITH MULTIBAND MODELS
|
||||
"use_mse_gan_loss": true,
|
||||
"use_hinge_gan_loss": false,
|
||||
"use_feat_match_loss": false, // use only with melgan discriminators
|
||||
|
||||
// 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,
|
||||
|
||||
// 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]
|
||||
},
|
||||
|
||||
"target_loss": "avg_G_loss", // loss value to pick the best model to save after each epoch
|
||||
|
||||
// DISCRIMINATOR
|
||||
"discriminator_model": "parallel_wavegan_discriminator",
|
||||
"discriminator_model_params":{
|
||||
"num_layers": 10
|
||||
},
|
||||
"steps_to_start_discriminator": 200000, // steps required to start GAN trainining.1
|
||||
|
||||
// GENERATOR
|
||||
"generator_model": "parallel_wavegan_generator",
|
||||
"generator_model_params": {
|
||||
"upsample_factors":[4, 4, 4, 4],
|
||||
"stacks": 3,
|
||||
"num_res_blocks": 30
|
||||
},
|
||||
|
||||
// DATASET
|
||||
"data_path": "/home/erogol/Data/LJSpeech-1.1/wavs/",
|
||||
"feature_path": null,
|
||||
"seq_len": 25600,
|
||||
"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": 6, // 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": 10000, // 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.
|
||||
"lr_gen": 0.0002, // Initial learning rate. If Noam decay is active, maximum learning rate.
|
||||
"lr_disc": 0.0002,
|
||||
"optimizer": "AdamW",
|
||||
"optimizer_params":{
|
||||
"betas": [0.8, 0.99],
|
||||
"weight_decay": 0.0
|
||||
},
|
||||
"lr_scheduler_gen": "ExponentialLR", // one of the schedulers from https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
|
||||
"lr_scheduler_gen_params": {
|
||||
"gamma": 0.999,
|
||||
"last_epoch": -1
|
||||
},
|
||||
"lr_scheduler_disc": "ExponentialLR", // one of the schedulers from https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
|
||||
"lr_scheduler_disc_params": {
|
||||
"gamma": 0.999,
|
||||
"last_epoch": -1
|
||||
},
|
||||
// TENSORBOARD and LOGGING
|
||||
"print_step": 25, // 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": false, // 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": 4, // number of training data loader processes. Don't set it too big. 4-8 are good values.
|
||||
"num_val_loader_workers": 4, // number of evaluation data loader processes.
|
||||
"eval_split_size": 10,
|
||||
|
||||
// PATHS
|
||||
"output_path": "/home/erogol/Models/LJSpeech/"
|
||||
}
|
||||
|
||||
|
|
@ -1,145 +0,0 @@
|
|||
{
|
||||
"run_name": "fullband-melgan",
|
||||
"run_description": "fullband 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": 24000, // 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": 0, // reference level db, theoretically 20db is the sound of air.
|
||||
|
||||
// Silence trimming
|
||||
"do_trim_silence": true,// 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": "/home/erogol/Data/libritts/LibriTTS/scale_stats.npy" // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored
|
||||
},
|
||||
|
||||
// DISTRIBUTED TRAINING
|
||||
"distributed":{
|
||||
"backend": "nccl",
|
||||
"url": "tcp:\/\/localhost:54324"
|
||||
},
|
||||
|
||||
// MODEL PARAMETERS
|
||||
"use_pqmf": false,
|
||||
|
||||
// LOSS PARAMETERS
|
||||
"use_stft_loss": true,
|
||||
"use_subband_stft_loss": false,
|
||||
"use_mse_gan_loss": true,
|
||||
"use_hinge_gan_loss": false,
|
||||
"use_feat_match_loss": false, // use only with melgan discriminators
|
||||
|
||||
// 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,
|
||||
|
||||
// multiscale stft loss parameters
|
||||
"stft_loss_params": {
|
||||
"n_ffts": [1024, 2048, 512],
|
||||
"hop_lengths": [120, 240, 50],
|
||||
"win_lengths": [600, 1200, 240]
|
||||
},
|
||||
|
||||
"target_loss": "avg_G_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": "fullband_melgan_generator",
|
||||
"generator_model_params": {
|
||||
"upsample_factors":[8, 8, 4],
|
||||
"num_res_blocks": 4
|
||||
},
|
||||
|
||||
// DATASET
|
||||
"data_path": "/home/erogol/Data/libritts/LibriTTS/train-clean-360/",
|
||||
"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": 48, // 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": 10000, // 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.
|
||||
"lr_gen": 0.0002, // Initial learning rate. If Noam decay is active, maximum learning rate.
|
||||
"lr_disc": 0.0002,
|
||||
"optimizer": "AdamW",
|
||||
"optimizer_params":{
|
||||
"betas": [0.8, 0.99],
|
||||
"weight_decay": 0.0
|
||||
},
|
||||
"lr_scheduler_gen": "ExponentialLR", // one of the schedulers from https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
|
||||
"lr_scheduler_gen_params": {
|
||||
"gamma": 0.999,
|
||||
"last_epoch": -1
|
||||
},
|
||||
"lr_scheduler_disc": "ExponentialLR", // one of the schedulers from https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
|
||||
"lr_scheduler_disc_params": {
|
||||
"gamma": 0.999,
|
||||
"last_epoch": -1
|
||||
},
|
||||
|
||||
// TENSORBOARD and LOGGING
|
||||
"print_step": 25, // 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": false, // 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": 4, // number of training data loader processes. Don't set it too big. 4-8 are good values.
|
||||
"num_val_loader_workers": 4, // number of evaluation data loader processes.
|
||||
"eval_split_size": 10,
|
||||
|
||||
// PATHS
|
||||
"output_path": "/home/erogol/Models/"
|
||||
}
|
||||
|
||||
|
||||
|
|
@ -1,118 +0,0 @@
|
|||
{
|
||||
"run_name": "wavegrad-libritts",
|
||||
"run_description": "wavegrad libritts",
|
||||
|
||||
"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": 24000, // 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": 0, // reference level db, theoretically 20db is the sound of air.
|
||||
|
||||
// Silence trimming
|
||||
"do_trim_silence": true,// 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": "/home/erogol/Data/libritts/LibriTTS/scale_stats_wavegrad.npy" // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored
|
||||
},
|
||||
|
||||
// DISTRIBUTED TRAINING
|
||||
"mixed_precision": true, // enable torch mixed precision training (true, false)
|
||||
"distributed":{
|
||||
"backend": "nccl",
|
||||
"url": "tcp:\/\/localhost:54322"
|
||||
},
|
||||
|
||||
"target_loss": "avg_wavegrad_loss", // loss value to pick the best model to save after each epoch
|
||||
|
||||
// MODEL PARAMETERS
|
||||
"generator_model": "wavegrad",
|
||||
"model_params":{
|
||||
"use_weight_norm": true,
|
||||
"y_conv_channels":32,
|
||||
"x_conv_channels":768,
|
||||
"ublock_out_channels": [512, 512, 256, 128, 128],
|
||||
"dblock_out_channels": [128, 128, 256, 512],
|
||||
"upsample_factors": [4, 4, 4, 2, 2],
|
||||
"upsample_dilations": [
|
||||
[1, 2, 1, 2],
|
||||
[1, 2, 1, 2],
|
||||
[1, 2, 4, 8],
|
||||
[1, 2, 4, 8],
|
||||
[1, 2, 4, 8]]
|
||||
},
|
||||
|
||||
// DATASET
|
||||
"data_path": "/home/erogol/Data/libritts/LibriTTS/train-clean-360/", // root data path. It finds all wav files recursively from there.
|
||||
"feature_path": null, // if you use precomputed features
|
||||
"seq_len": 6144, // 24 * hop_length
|
||||
"pad_short": 0, // additional padding for short wavs
|
||||
"conv_pad": 0, // additional padding against convolutions applied to spectrograms
|
||||
"use_noise_augment": false, // add noise to the audio signal for augmentation
|
||||
"use_cache": false, // use in memory cache to keep the computed features. This might cause OOM.
|
||||
|
||||
"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": 96, // Batch size for training.
|
||||
|
||||
// NOISE SCHEDULE PARAMS - Only effective at training time.
|
||||
"train_noise_schedule":{
|
||||
"min_val": 1e-6,
|
||||
"max_val": 1e-2,
|
||||
"num_steps": 1000
|
||||
},
|
||||
"test_noise_schedule":{
|
||||
"min_val": 1e-6,
|
||||
"max_val": 1e-2,
|
||||
"num_steps": 50
|
||||
},
|
||||
|
||||
// VALIDATION
|
||||
"run_eval": true, // enable/disable evaluation run
|
||||
|
||||
// OPTIMIZER
|
||||
"epochs": 10000, // total number of epochs to train.
|
||||
"clip_grad": 1.0, // Generator gradient clipping threshold. Apply gradient clipping if > 0
|
||||
"lr_scheduler": "MultiStepLR", // one of the schedulers from https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
|
||||
"lr_scheduler_params": {
|
||||
"gamma": 0.5,
|
||||
"milestones": [100000, 200000, 300000, 400000, 500000, 600000]
|
||||
},
|
||||
"lr": 1e-4, // Initial learning rate. If Noam decay is active, maximum learning rate.
|
||||
|
||||
// TENSORBOARD and LOGGING
|
||||
"print_step": 50, // 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": 5000, // 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": false, // 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": true, // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
|
||||
|
||||
// DATA LOADING
|
||||
"num_loader_workers": 4, // number of training data loader processes. Don't set it too big. 4-8 are good values.
|
||||
"num_val_loader_workers": 4, // number of evaluation data loader processes.
|
||||
"eval_split_size": 256,
|
||||
|
||||
// PATHS
|
||||
"output_path": "/home/erogol/Models/LJSpeech/"
|
||||
}
|
||||
|
||||
|
|
@ -1,103 +0,0 @@
|
|||
{
|
||||
"run_name": "wavernn_librittts",
|
||||
"run_description": "wavernn libritts training from LJSpeech model",
|
||||
|
||||
// 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": 24000, // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled.
|
||||
"preemphasis": 0.98, // 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.
|
||||
// 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": 40.0, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
|
||||
"mel_fmax": 8000.0, // maximum freq level for mel-spec. Tune for dataset!!
|
||||
"spec_gain": 20.0, // 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 // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored
|
||||
},
|
||||
|
||||
// Generating / Synthesizing
|
||||
"batched": true,
|
||||
"target_samples": 11000, // target number of samples to be generated in each batch entry
|
||||
"overlap_samples": 550, // number of samples for crossfading between batches
|
||||
// DISTRIBUTED TRAINING
|
||||
// "distributed":{
|
||||
// "backend": "nccl",
|
||||
// "url": "tcp:\/\/localhost:54321"
|
||||
// },
|
||||
|
||||
// MODEL MODE
|
||||
"mode": "mold", // mold [string], gauss [string], bits [int]
|
||||
"mulaw": true, // apply mulaw if mode is bits
|
||||
|
||||
// MODEL PARAMETERS
|
||||
"wavernn_model_params": {
|
||||
"rnn_dims": 512,
|
||||
"fc_dims": 512,
|
||||
"compute_dims": 128,
|
||||
"res_out_dims": 128,
|
||||
"num_res_blocks": 10,
|
||||
"use_aux_net": true,
|
||||
"use_upsample_net": true,
|
||||
"upsample_factors": [4, 8, 8] // this needs to correctly factorise hop_length
|
||||
},
|
||||
|
||||
// GENERATOR - for backward compatibility
|
||||
"generator_model": "WaveRNN",
|
||||
|
||||
// DATASET
|
||||
//"use_gta": true, // use computed gta features from the tts model
|
||||
"data_path": "/home/erogol/Data/libritts/LibriTTS/train-clean-360/", // path containing training wav files
|
||||
"feature_path": null, // path containing computed features from wav files if null compute them
|
||||
"seq_len": 1280, // has to be devideable by hop_length
|
||||
"padding": 2, // pad the input for resnet to see wider input length
|
||||
|
||||
// TRAINING
|
||||
"batch_size": 256, // Batch size for training.
|
||||
"epochs": 10000, // total number of epochs to train.
|
||||
"mixed_precision": true, // enable/ disable mixed precision training
|
||||
|
||||
// VALIDATION
|
||||
"run_eval": true,
|
||||
"test_every_epochs": 10, // Test after set number of epochs (Test every 10 epochs for example)
|
||||
|
||||
// OPTIMIZER
|
||||
"grad_clip": 4, // apply gradient clipping if > 0
|
||||
"lr_scheduler": "MultiStepLR", // one of the schedulers from https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
|
||||
"lr_scheduler_params": {
|
||||
"gamma": 0.5,
|
||||
"milestones": [200000, 400000, 600000]
|
||||
},
|
||||
"lr": 1e-4, // initial learning rate
|
||||
|
||||
// TENSORBOARD and LOGGING
|
||||
"print_step": 25, // 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": false, // 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": 4, // number of training data loader processes. Don't set it too big. 4-8 are good values.
|
||||
"num_val_loader_workers": 4, // number of evaluation data loader processes.
|
||||
"eval_split_size": 50, // number of samples for testing
|
||||
|
||||
// PATHS
|
||||
"output_path": "/home/erogol/Models/LJSpeech/"
|
||||
}
|
||||
Loading…
Reference in New Issue