hyperparams.yaml

# Generated 2022-10-08 from:
# /home/xportes/projects/speechbrain/recipes/LJSpeech/TTS/tacotron2/hparams/train.yaml
# yamllint disable
############################################################################
# Model: Tacotron2
# Tokens: Raw characters (English text)
# losses: Transducer
# Training: LJSpeech
# Authors: Georges Abous-Rjeili, Artem Ploujnikov, Yingzhi Wang
# ############################################################################


###################################
# Experiment Parameters and setup #
###################################
seed: 9234
__set_seed: !apply:torch.manual_seed [9234]
output_folder: ./results/tacotron2/9234
save_folder: ./results/tacotron2/9234/save
train_log: ./results/tacotron2/9234/train_log.txt
epochs: 750
keep_checkpoint_interval: 50

###################################
# Progress Samples                #
###################################
# Progress samples are used to monitor the progress
# of an ongoing training session by outputting samples
# of spectrograms, alignments, etc at regular intervals

# Whether to enable progress samples
progress_samples: true

# The path where the samples will be stored
progress_sample_path: ./results/tacotron2/9234/samples
# The interval, in epochs. For instance, if it is set to 5,
# progress samples will be output every 5 epochs
progress_samples_interval: 1
# The sample size for raw batch samples saved in batch.pth
# (useful mostly for model debugging)
progress_batch_sample_size: 3

#################################
# Data files and pre-processing #
#################################
data_folder: ../../../../LJSpeech-1.1
                          # e.g, /localscratch/ljspeech

train_json: ./results/tacotron2/9234/save/train.json
valid_json: ./results/tacotron2/9234/save/valid.json
test_json: ./results/tacotron2/9234/save/test.json

splits: [train, valid]
split_ratio: [90, 10]

skip_prep: false

# Use the original preprocessing from nvidia
# The cleaners to be used (applicable to nvidia only)
text_cleaners: [english_cleaners]

################################
# Audio Parameters             #
################################
sample_rate: 22050
hop_length: 256
win_length: 1024
n_mel_channels: 80
n_fft: 1024
mel_fmin: 0.0
mel_fmax: 8000.0
mel_normalized:
power: 1
norm: slaney
mel_scale: slaney
dynamic_range_compression: true

################################
# Optimization Hyperparameters #
################################
learning_rate: 0.001
weight_decay: 0.000006
batch_size: 64 #minimum 2
mask_padding: true
guided_attention_sigma: 0.2
guided_attention_weight: 50.0
guided_attention_weight_half_life: 10.
guided_attention_hard_stop: 50
gate_loss_weight: 1.0

train_dataloader_opts:
  batch_size: 64
  drop_last: false  #True #False
  num_workers: 8
  collate_fn: !new:speechbrain.lobes.models.Tacotron2.TextMelCollate

valid_dataloader_opts:
  batch_size: 64
  num_workers: 8
  collate_fn: !new:speechbrain.lobes.models.Tacotron2.TextMelCollate

test_dataloader_opts:
  batch_size: 64
  num_workers: 8
  collate_fn: !new:speechbrain.lobes.models.Tacotron2.TextMelCollate

################################
# Model Parameters and model   #
################################
n_symbols: 150 #fixed depending on symbols in textToSequence
symbols_embedding_dim: 512

# Encoder parameters
encoder_kernel_size: 5
encoder_n_convolutions: 3
encoder_embedding_dim: 512

# Decoder parameters
# The number of frames in the target per encoder step
n_frames_per_step: 1
decoder_rnn_dim: 1024
prenet_dim: 256
max_decoder_steps: 1000
gate_threshold: 0.5
p_attention_dropout: 0.1
p_decoder_dropout: 0.1
decoder_no_early_stopping: false

# Attention parameters
attention_rnn_dim: 1024
attention_dim: 128

# Location Layer parameters
attention_location_n_filters: 32
attention_location_kernel_size: 31

# Mel-post processing network parameters
postnet_embedding_dim: 512
postnet_kernel_size: 5
postnet_n_convolutions: 5

mel_spectogram: !name:speechbrain.lobes.models.Tacotron2.mel_spectogram
  sample_rate: 22050
  hop_length: 256
  win_length: 1024
  n_fft: 1024
  n_mels: 80
  f_min: 0.0
  f_max: 8000.0
  power: 1
  normalized:
  norm: slaney
  mel_scale: slaney
  compression: true

#model
model: &id002 !new:speechbrain.lobes.models.Tacotron2.Tacotron2

#optimizer
  mask_padding: true
  n_mel_channels: 80
  # symbols
  n_symbols: 150
  symbols_embedding_dim: 512
  # encoder
  encoder_kernel_size: 5
  encoder_n_convolutions: 3
  encoder_embedding_dim: 512
  # attention
  attention_rnn_dim: 1024
  attention_dim: 128
  # attention location
  attention_location_n_filters: 32
  attention_location_kernel_size: 31
  # decoder
  n_frames_per_step: 1
  decoder_rnn_dim: 1024
  prenet_dim: 256
  max_decoder_steps: 1000
  gate_threshold: 0.5
  p_attention_dropout: 0.1
  p_decoder_dropout: 0.1
  # postnet
  postnet_embedding_dim: 512
  postnet_kernel_size: 5
  postnet_n_convolutions: 5
  decoder_no_early_stopping: false

guided_attention_scheduler: &id001 !new:speechbrain.nnet.schedulers.StepScheduler
  initial_value: 50.0
  half_life: 10.

criterion: !new:speechbrain.lobes.models.Tacotron2.Loss
  gate_loss_weight: 1.0
  guided_attention_weight: 50.0
  guided_attention_sigma: 0.2
  guided_attention_scheduler: *id001
  guided_attention_hard_stop: 50

modules:
  model: *id002
opt_class: !name:torch.optim.Adam
  lr: 0.001
  weight_decay: 0.000006

#epoch object
epoch_counter: &id003 !new:speechbrain.utils.epoch_loop.EpochCounter
  limit: 750

train_logger: !new:speechbrain.utils.train_logger.FileTrainLogger
  save_file: ./results/tacotron2/9234/train_log.txt

#annealing_function
lr_annealing: &id004 !new:speechbrain.nnet.schedulers.IntervalScheduler

#infer: !name:speechbrain.lobes.models.Tacotron2.infer

  intervals:
  - steps: 6000
    lr: 0.0005
  - steps: 8000
    lr: 0.0003
  - steps: 10000
    lr: 0.0001

#checkpointer
checkpointer: !new:speechbrain.utils.checkpoints.Checkpointer
  checkpoints_dir: ./results/tacotron2/9234/save
  recoverables:
    model: *id002
    counter: *id003
    scheduler: *id004
progress_sample_logger: !new:speechbrain.utils.train_logger.ProgressSampleLogger
  output_path: ./results/tacotron2/9234/samples
  batch_sample_size: 3
  formats:
    raw_batch: raw

text_to_sequence: !name:text_to_sequence.text_to_sequence

pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
  loadables:
    model: !ref <model>
  paths:
    model: Daporte/speechbrain_tacotron2_exp/model.ckpt