Skip to content

[WIP] Zwf training modifications (for reference) #178

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 9 commits into
base: master
Choose a base branch
from
Open

[WIP] Zwf training modifications (for reference) #178

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
9ec46d7
bugfix and reduce deps
zachwe Jun 29, 2023
7d6c13e
some minor changes
zachwe Jun 30, 2023
0f2a00a
qol improvements
zachwe Jul 1, 2023
f1dfced
logging
zachwe Jul 10, 2023
11afbb1
some useful things
zachwe Jul 13, 2023
5a10376
configs
zachwe Aug 15, 2023
6c212e9
save
zachwe Aug 16, 2023
d3516ca
fix
sjkoelle Sep 7, 2023
d19fee0
save
sjkoelle Sep 7, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
149 changes: 149 additions & 0 deletions configs/config-ljspeech.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,149 @@
{
"train_config": {
"output_directory": "/home/zach/code/uberduck-ml-dev/outputs-2023-07-12-ljspeech/",
"epochs": 10000000,
"optim_algo": "RAdam",
"learning_rate": 0.0001,
"weight_decay": 1e-6,
"sigma": 1.0,
"iters_per_checkpoint": 2500,
"batch_size": 16,
"seed": null,
"checkpoint_path": "",
"ignore_layers": [],
"ignore_layers_warmstart": [],
"steps_per_sample": 500,
"finetune_layers": [],
"include_layers": [],
"vocoder_config_path": "/home/zach/code/uberduck-ml-dev/models/hifi_gan_config.json",
"vocoder_checkpoint_path": "/home/zach/code/uberduck-ml-dev/models/g_hifi_crust",
"log_attribute_samples": false,
"log_decoder_samples": true,
"warmstart_checkpoint_path": "/home/zach/code/uberduck-ml-dev/outputs-2023-07-12-ljspeech/model_2500.pt",
"______warmstartasdf": "/home/zach/code/uberduck-ml-dev/outputs/model_115000.pt",
"use_amp": true,
"grad_clip_val": 1.0,
"loss_weights": {
"blank_logprob": -1,
"ctc_loss_weight": 0.1,
"binarization_loss_weight": 1.0,
"dur_loss_weight": 1.0,
"f0_loss_weight": 1.0,
"energy_loss_weight": 1.0,
"vpred_loss_weight": 1.0
},
"binarization_start_iter": 6000,
"kl_loss_start_iter": 8000,
"unfreeze_modules": "all"
},
"data_config": {
"training_files": {
"lj": {
"basedir": "/home/zach/code/uberduck-ml-dev/data",
"audiodir": "",
"filelist": "/home/zach/code/uberduck-ml-dev/filelists/lj-filelist.txt",
"lmdbpath": ""
}
},
"validation_files": {},
"dur_min": 0.1,
"dur_max": 10.2,
"sampling_rate": 22050,
"filter_length": 1024,
"hop_length": 256,
"win_length": 1024,
"n_mel_channels": 80,
"mel_fmin": 0.0,
"mel_fmax": 8000.0,
"f0_min": 80.0,
"f0_max": 640.0,
"max_wav_value": 32768.0,
"use_f0": true,
"use_log_f0": 0,
"use_energy_avg": true,
"use_scaled_energy": true,
"symbol_set": "radtts",
"cleaner_names": ["radtts_cleaners"],
"heteronyms_path": "/home/zach/code/uberduck-ml-dev/uberduck_ml_dev/text/heteronyms",
"phoneme_dict_path": "/home/zach/code/uberduck-ml-dev/uberduck_ml_dev/text/cmudict-0.7b",
"p_phoneme": 1.0,
"handle_phoneme": "word",
"handle_phoneme_ambiguous": "ignore",
"include_speakers": null,
"n_frames": -1,
"betabinom_cache_path": "/home/zach/code/uberduck-ml-dev/data_cache/",
"lmdb_cache_path": "",
"use_attn_prior_masking": true,
"prepend_space_to_text": true,
"append_space_to_text": true,
"add_bos_eos_to_text": false,
"betabinom_scaling_factor": 1.0,
"distance_tx_unvoiced": false,
"is_zero_shot": false,
"mel_noise_scale": 0.0
},
"dist_config": {
"dist_backend": "nccl",
"dist_url": "tcp://localhost:54321"
},
"model_config": {
"n_speakers": 1,
"n_speaker_dim": 16,
"n_text": 185,
"n_text_dim": 512,
"n_flows": 8,
"n_conv_layers_per_step": 4,
"n_mel_channels": 80,
"n_hidden": 1024,
"mel_encoder_n_hidden": 512,
"dummy_speaker_embedding": false,
"n_early_size": 2,
"n_early_every": 2,
"n_group_size": 2,
"affine_model": "wavenet",
"include_modules": "decatn",
"scaling_fn": "tanh",
"matrix_decomposition": "LUS",
"learn_alignments": true,
"use_speaker_emb_for_alignment": false,
"attn_straight_through_estimator": true,
"use_context_lstm": true,
"context_lstm_norm": "spectral",
"context_lstm_w_f0_and_energy": true,
"text_encoder_lstm_norm": "spectral",
"n_f0_dims": 1,
"n_energy_avg_dims": 1,
"use_first_order_features": false,
"unvoiced_bias_activation": "relu",
"decoder_use_partial_padding": true,
"decoder_use_unvoiced_bias": true,
"ap_pred_log_f0": true,
"ap_use_unvoiced_bias": true,
"ap_use_voiced_embeddings": true,
"dur_model_config": null,
"f0_model_config": null,
"energy_model_config": null,
"v_model_config": {
"name": "dap",
"hparams": {
"n_speaker_dim": 16,
"take_log_of_input": false,
"bottleneck_hparams": {
"in_dim": 512,
"reduction_factor": 16,
"norm": "weightnorm",
"non_linearity": "relu"
},
"arch_hparams": {
"out_dim": 1,
"n_layers": 2,
"n_channels": 256,
"kernel_size": 3,
"p_dropout": 0.5,
"lstm_type": "",
"use_linear": 1
}
}
}
}
}
149 changes: 149 additions & 0 deletions configs/config-zeroshot-warmstart.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,149 @@
{
"train_config": {
"output_directory": "/home/zach/code/uberduck-ml-dev/outputs-2023-07-13-zeroshot-warmstart/",
"epochs": 10000000,
"optim_algo": "RAdam",
"learning_rate": 0.0001,
"weight_decay": 1e-6,
"sigma": 1.0,
"iters_per_checkpoint": 2500,
"batch_size": 16,
"seed": null,
"checkpoint_path": "",
"ignore_layers": [],
"ignore_layers_warmstart": [],
"steps_per_sample": 500,
"finetune_layers": [],
"include_layers": [],
"vocoder_config_path": "/home/zach/code/uberduck-ml-dev/models/hifi_gan_config.json",
"vocoder_checkpoint_path": "/home/zach/code/uberduck-ml-dev/models/g_hifi_crust",
"log_attribute_samples": false,
"log_decoder_samples": true,
"warmstart_checkpoint_path": "/home/zach/code/uberduck-ml-dev/outputs-2023-07-12-zeroshot/model_40000.pt",
"______warmstartasdf": "/home/zach/code/uberduck-ml-dev/outputs/model_115000.pt",
"use_amp": true,
"grad_clip_val": 1.0,
"loss_weights": {
"blank_logprob": -1,
"ctc_loss_weight": 0.1,
"binarization_loss_weight": 1.0,
"dur_loss_weight": 1.0,
"f0_loss_weight": 1.0,
"energy_loss_weight": 1.0,
"vpred_loss_weight": 1.0
},
"binarization_start_iter": 6000,
"kl_loss_start_iter": 8000,
"unfreeze_modules": "all"
},
"data_config": {
"training_files": {
"vctk": {
"basedir": "/home/zach/code/uberduck-ml-dev/data",
"audiodir": "",
"filelist": "/home/zach/code/uberduck-ml-dev/filelists/vctk-radtts.txt",
"lmdbpath": ""
}
},
"validation_files": {},
"dur_min": 0.1,
"dur_max": 10.2,
"sampling_rate": 22050,
"filter_length": 1024,
"hop_length": 256,
"win_length": 1024,
"n_mel_channels": 80,
"mel_fmin": 0.0,
"mel_fmax": 8000.0,
"f0_min": 80.0,
"f0_max": 640.0,
"max_wav_value": 32768.0,
"use_f0": true,
"use_log_f0": 0,
"use_energy_avg": true,
"use_scaled_energy": true,
"symbol_set": "radtts",
"cleaner_names": ["radtts_cleaners"],
"heteronyms_path": "/home/zach/code/uberduck-ml-dev/uberduck_ml_dev/text/heteronyms",
"phoneme_dict_path": "/home/zach/code/uberduck-ml-dev/uberduck_ml_dev/text/cmudict-0.7b",
"p_phoneme": 1.0,
"handle_phoneme": "word",
"handle_phoneme_ambiguous": "ignore",
"include_speakers": null,
"n_frames": -1,
"betabinom_cache_path": "/home/zach/code/uberduck-ml-dev/data_cache/",
"lmdb_cache_path": "",
"use_attn_prior_masking": true,
"prepend_space_to_text": true,
"append_space_to_text": true,
"add_bos_eos_to_text": false,
"betabinom_scaling_factor": 1.0,
"distance_tx_unvoiced": false,
"is_zero_shot": true,
"mel_noise_scale": 0.0
},
"dist_config": {
"dist_backend": "nccl",
"dist_url": "tcp://localhost:54321"
},
"model_config": {
"n_speakers": 0,
"n_speaker_dim": 512,
"n_text": 185,
"n_text_dim": 512,
"n_flows": 8,
"n_conv_layers_per_step": 4,
"n_mel_channels": 80,
"n_hidden": 1024,
"mel_encoder_n_hidden": 512,
"dummy_speaker_embedding": false,
"n_early_size": 2,
"n_early_every": 2,
"n_group_size": 2,
"affine_model": "wavenet",
"include_modules": "decatn",
"scaling_fn": "tanh",
"matrix_decomposition": "LUS",
"learn_alignments": true,
"use_speaker_emb_for_alignment": false,
"attn_straight_through_estimator": true,
"use_context_lstm": true,
"context_lstm_norm": "spectral",
"context_lstm_w_f0_and_energy": true,
"text_encoder_lstm_norm": "spectral",
"n_f0_dims": 1,
"n_energy_avg_dims": 1,
"use_first_order_features": false,
"unvoiced_bias_activation": "relu",
"decoder_use_partial_padding": true,
"decoder_use_unvoiced_bias": true,
"ap_pred_log_f0": true,
"ap_use_unvoiced_bias": true,
"ap_use_voiced_embeddings": true,
"dur_model_config": null,
"f0_model_config": null,
"energy_model_config": null,
"v_model_config": {
"name": "dap",
"hparams": {
"n_speaker_dim": 16,
"take_log_of_input": false,
"bottleneck_hparams": {
"in_dim": 512,
"reduction_factor": 16,
"norm": "weightnorm",
"non_linearity": "relu"
},
"arch_hparams": {
"out_dim": 1,
"n_layers": 2,
"n_channels": 256,
"kernel_size": 3,
"p_dropout": 0.5,
"lstm_type": "",
"use_linear": 1
}
}
}
}
}
Loading