File size: 11,118 Bytes
3eed963 |
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 |
CONFIG
├── data
│ └── _target_: matcha.data.text_mel_datamodule.TextMelDataModule
│ name: ljspeech
│ train_filelist_path: data/LJSpeech-1.1/train.txt
│ valid_filelist_path: data/LJSpeech-1.1/val.txt
│ batch_size: 32
│ num_workers: 20
│ pin_memory: true
│ cleaners:
│ - english_cleaners2
│ add_blank: true
│ n_spks: 1
│ n_fft: 1024
│ n_feats: 80
│ sample_rate: 22050
│ hop_length: 256
│ win_length: 1024
│ f_min: 0
│ f_max: 8000
│ data_statistics:
│ mel_mean: -5.536622
│ mel_std: 2.116101
│ seed: 1234
│ load_durations: false
│
├── model
│ └── _target_: matcha.models.matcha_tts.MatchaTTS
│ n_vocab: 178
│ n_spks: 1
│ spk_emb_dim: 64
│ n_feats: 80
│ data_statistics:
│ mel_mean: -5.536622
│ mel_std: 2.116101
│ out_size: null
│ prior_loss: true
│ use_precomputed_durations: false
│ encoder:
│ encoder_type: RoPE Encoder
│ encoder_params:
│ n_feats: 80
│ n_channels: 192
│ filter_channels: 768
│ filter_channels_dp: 256
│ n_heads: 2
│ n_layers: 6
│ kernel_size: 3
│ p_dropout: 0.1
│ spk_emb_dim: 64
│ n_spks: 1
│ prenet: true
│ duration_predictor_params:
│ filter_channels_dp: 256
│ kernel_size: 3
│ p_dropout: 0.1
│ decoder:
│ channels:
│ - 256
│ - 256
│ dropout: 0.05
│ attention_head_dim: 64
│ n_blocks: 1
│ num_mid_blocks: 2
│ num_heads: 2
│ act_fn: snakebeta
│ cfm:
│ name: CFM
│ solver: euler
│ sigma_min: 0.0001
│ optimizer:
│ _target_: torch.optim.Adam
│ _partial_: true
│ lr: 0.0001
│ weight_decay: 0.0
│
├── callbacks
│ └── model_checkpoint:
│ _target_: lightning.pytorch.callbacks.ModelCheckpoint
│ dirpath: /workspace/Matcha-TTS/logs/train/ljspeech/runs/2024-10-19_19-
│ filename: checkpoint_{epoch:03d}
│ monitor: epoch
│ verbose: false
│ save_last: true
│ save_top_k: 10
│ mode: max
│ auto_insert_metric_name: true
│ save_weights_only: false
│ every_n_train_steps: null
│ train_time_interval: null
│ every_n_epochs: 100
│ save_on_train_epoch_end: null
│ model_summary:
│ _target_: lightning.pytorch.callbacks.RichModelSummary
│ max_depth: 3
│ rich_progress_bar:
│ _target_: lightning.pytorch.callbacks.RichProgressBar
│
├── logger
│ └── tensorboard:
│ _target_: lightning.pytorch.loggers.tensorboard.TensorBoardLogger
│ save_dir: /workspace/Matcha-TTS/logs/train/ljspeech/runs/2024-10-19_19
│ name: null
│ log_graph: false
│ default_hp_metric: true
│ prefix: ''
│
├── trainer
│ └── _target_: lightning.pytorch.trainer.Trainer
│ default_root_dir: /workspace/Matcha-TTS/logs/train/ljspeech/runs/2024-10
│ max_epochs: -1
│ accelerator: gpu
│ devices:
│ - 0
│ precision: 16-mixed
│ check_val_every_n_epoch: 1
│ deterministic: false
│ gradient_clip_val: 5.0
│
├── paths
│ └── root_dir: /workspace/Matcha-TTS
│ data_dir: /workspace/Matcha-TTS/data/
│ log_dir: /workspace/Matcha-TTS/logs/
│ output_dir: /workspace/Matcha-TTS/logs/train/ljspeech/runs/2024-10-19_19
│ work_dir: /workspace/Matcha-TTS
│
├── extras
│ └── ignore_warnings: false
│ enforce_tags: true
│ print_config: true
│
├── task_name
│ └── train
├── run_name
│ └── ljspeech
├── tags
│ └── ['ljspeech']
├── train
│ └── True
├── test
│ └── True
├── ckpt_path
│ └── None
└── seed
└── 1234
|