diff_tts_test.yaml

# @package _global_

# To pick dataset path execute with: ++datamodule.dataset.path=/your_wav_root/

sampling_rate: 16000
length: 131072
channels: 1
log_every_n_steps: 1000

model:
  _target_: main.module_diff_tts.Model
  lr: 1e-4
  lr_beta1: 0.95
  lr_beta2: 0.999
  lr_eps: 1e-6
  lr_weight_decay: 1e-3
  ema_beta: 0.9999
  ema_power: 0.7

  model:
    _target_: audio_diffusion_pytorch.AudioDiffusionModel
    in_channels: ${channels}
    channels: 128
    patch_size: 16
    resnet_groups: 8
    kernel_multiplier_downsample: 2
    multipliers: [1, 2, 4, 4, 4, 4, 4]
    factors: [2, 2, 2, 2, 2, 2]
    num_blocks: [2, 2, 2, 2, 2, 2]
    attentions: [0, 0, 0, 1, 1, 1, 1]
    attention_heads: 8
    attention_features: 64
    attention_multiplier: 2
    use_nearest_upsample: False
    use_skip_scale: True
    context_channels: [0, 0, 0, 0, 512]
    diffusion_type: v
    diffusion_sigma_distribution:
      _target_: audio_diffusion_pytorch.UniformDistribution

  autoencoder:
    _target_: audio_diffusion_pytorch.AutoEncoder1d
    in_channels: ${channels}
    channels: 128
    patch_factor: 16
    patch_blocks: 1
    resnet_groups: 8
    multipliers: [1, 2, 4, 4, 4]
    factors: [2, 2, 2, 2]
    num_blocks: [4, 4, 4, 4]

  tokenizer: google/byt5-base

  text_embedding:
    _target_: torch.nn.Embedding
    num_embeddings: 260
    embedding_dim: 512

  text_encoder:
    _target_: a_transformers_pytorch.transformers.Transformer
    max_length: 256
    features: 512
    num_layers: 8
    head_features: 64
    num_heads: 8
    multiplier: 4

  speech_posemb:
    _target_: a_transformers_pytorch.transformers.AbsolutePositionalEmbedding
    features: 512
    max_length: 512



datamodule:
  _target_: main.module_diff_tts.Datamodule
  dataset:
    _target_: audio_data_pytorch.CommonVoiceDataset
    auth_token: ${oc.env:HUGGINGFACE_TOKEN}
    root: ${data_dir}
    version: 1
    languages: ["it"]
    with_info: True
    transforms:
      _target_: audio_data_pytorch.AllTransform
      source_rate: 48000
      target_rate: ${sampling_rate}
      crop_size: ${length}
  val_split: 0.01
  batch_size: 4
  num_workers: 8
  pin_memory: True

callbacks:
  rich_progress_bar:
    _target_: pytorch_lightning.callbacks.RichProgressBar

  model_checkpoint:
    _target_: pytorch_lightning.callbacks.ModelCheckpoint
    monitor: "valid_loss"   # name of the logged metric which determines when model is improving
    save_top_k: 1           # save k best models (determined by above metric)
    save_last: True         # additionaly always save model from last epoch
    mode: "min"             # can be "max" or "min"
    verbose: False
    dirpath: ${logs_dir}/ckpts/${now:%Y-%m-%d-%H-%M-%S}
    filename: '{epoch:02d}-{valid_loss:.3f}'

  model_summary:
    _target_: pytorch_lightning.callbacks.RichModelSummary
    max_depth: 2

  audio_samples_logger:
    _target_: main.module_diff_tts.SampleLogger
    num_items: 3
    channels: ${channels}
    sampling_rate: ${sampling_rate}
    length: ${length}
    sampling_steps: [3,5,10,25,50,100]
    use_ema_model: False
    diffusion_sampler:
      _target_: audio_diffusion_pytorch.VSampler
    diffusion_schedule:
      _target_: audio_diffusion_pytorch.LinearSchedule

loggers:
  wandb:
    _target_: pytorch_lightning.loggers.wandb.WandbLogger
    project: ${oc.env:WANDB_PROJECT}
    entity: ${oc.env:WANDB_ENTITY}
    # offline: False  # set True to store all logs only locally
    job_type: "train"
    group: ""
    save_dir: ${logs_dir}

trainer:
  _target_: pytorch_lightning.Trainer
  gpus: 0 # Set `1` to train on GPU, `0` to train on CPU only, and `-1` to train on all GPUs, default `0`
  precision: 32 # Precision used for tensors, default `32`
  accelerator: null # `ddp` GPUs train individually and sync gradients, default `None`
  min_epochs: 0
  max_epochs: -1
  enable_model_summary: False
  log_every_n_steps: 1 # Logs metrics every N batches
  check_val_every_n_epoch: null
  val_check_interval: ${log_every_n_steps}