end

checkpoints/checkpoint_epoch=399.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1151cd7c9ce36258a5e8f125471dd33f32ffddcee137bf11f14b052cd1089fb6
+size 218840327

checkpoints/checkpoint_epoch=499.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802947c447968f893cfafb4c3361c8641c671f665225ef7fc867cf18b1f2c16f
+size 218840710

checkpoints/checkpoint_epoch=599.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed2174b0a971098edb110d40815a0013e9c29ab119f7d3cde9cdfb8853d1a61
+size 218841029

checkpoints/checkpoint_epoch=699.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a076f2cc33d47a6707c19aba5587c693b878ebb0e0e3d17988f083f9e6d8e2
+size 218841412

checkpoints/checkpoint_epoch=799.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d6ac3da37a1e63557ad4dd50e85fe9132d15a2dbe3df705c10f26b0403f488
+size 218841795

checkpoints/checkpoint_epoch=899.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68cd1ce3255316a71119ba608db65cce3a3dba1d401ec000ad685025c962720
+size 218842178

checkpoints/last.ckpt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:284eb05eb7e8339ede808586d0bf3befa6fa81e23f68ffcaeae71d4c9081fa23
-size 218839944
+oid sha256:adb0b628157cf3e905bbe39cee8de969d52a024fa014fe98e83a5e35a3f06acf
+size 218842178

tensorboard/version_0/events.out.tfevents.1729366325.0959f84f9bd7.22.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d476c573f8ba1e26d791499bd0a9472e47c9fe2eab99ad52d0e43ca8d327f369
+size 518352307

tensorboard/version_0/hparams.yaml

@@ -0,0 +1,115 @@
+model:
+  _target_: matcha.models.matcha_tts.MatchaTTS
+  n_vocab: 178
+  n_spks: ${data.n_spks}
+  spk_emb_dim: 64
+  n_feats: 80
+  data_statistics: ${data.data_statistics}
+  out_size: null
+  prior_loss: true
+  use_precomputed_durations: ${data.load_durations}
+  encoder:
+    encoder_type: RoPE Encoder
+    encoder_params:
+      n_feats: ${model.n_feats}
+      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: ${model.encoder.encoder_params.filter_channels_dp}
+      kernel_size: 3
+      p_dropout: ${model.encoder.encoder_params.p_dropout}
+  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
+model/params/total: 18204193
+model/params/trainable: 18204193
+model/params/non_trainable: 0
+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: ${seed}
+  load_durations: false
+trainer:
+  _target_: lightning.pytorch.trainer.Trainer
+  default_root_dir: ${paths.output_dir}
+  max_epochs: -1
+  accelerator: gpu
+  devices:
+  - 0
+  precision: 16-mixed
+  check_val_every_n_epoch: 1
+  deterministic: false
+  gradient_clip_val: 5.0
+callbacks:
+  model_checkpoint:
+    _target_: lightning.pytorch.callbacks.ModelCheckpoint
+    dirpath: ${paths.output_dir}/checkpoints
+    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
+extras:
+  ignore_warnings: false
+  enforce_tags: true
+  print_config: true
+task_name: train
+tags:
+- ljspeech
+ckpt_path: null
+seed: 1234

train.log

@@ -11,3 +11,43 @@
 [2024-10-19 19:32:05,026][__main__][INFO] - Instantiating trainer <lightning.pytorch.trainer.Trainer>
 [2024-10-19 19:32:05,116][__main__][INFO] - Logging hyperparameters!
 [2024-10-19 19:32:05,170][__main__][INFO] - Starting training!
+[2024-10-22 01:31:05,786][matcha.utils.utils][ERROR] - 
+Traceback (most recent call last):
+  File "/workspace/Matcha-TTS/matcha/utils/utils.py", line 77, in wrap
+    metric_dict, object_dict = task_func(cfg=cfg)
+  File "/workspace/Matcha-TTS/matcha/train.py", line 79, in train
+    trainer.fit(model=model, datamodule=datamodule, ckpt_path=cfg.get("ckpt_path"))
+  File "/opt/conda/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 538, in fit
+    call._call_and_handle_interrupt(
+  File "/opt/conda/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 47, in _call_and_handle_interrupt
+    return trainer_fn(*args, **kwargs)
+  File "/opt/conda/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 574, in _fit_impl
+    self._run(model, ckpt_path=ckpt_path)
+  File "/opt/conda/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 981, in _run
+    results = self._run_stage()
+  File "/opt/conda/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1025, in _run_stage
+    self.fit_loop.run()
+  File "/opt/conda/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 206, in run
+    self.on_advance_end()
+  File "/opt/conda/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py", line 378, in on_advance_end
+    call._call_callback_hooks(trainer, "on_train_epoch_end", monitoring_callbacks=True)
+  File "/opt/conda/lib/python3.10/site-packages/lightning/pytorch/trainer/call.py", line 218, in _call_callback_hooks
+    fn(trainer, trainer.lightning_module, *args, **kwargs)
+  File "/opt/conda/lib/python3.10/site-packages/lightning/pytorch/callbacks/model_checkpoint.py", line 326, in on_train_epoch_end
+    self._save_last_checkpoint(trainer, monitor_candidates)
+  File "/opt/conda/lib/python3.10/site-packages/lightning/pytorch/callbacks/model_checkpoint.py", line 696, in _save_last_checkpoint
+    self._save_checkpoint(trainer, filepath)
+  File "/opt/conda/lib/python3.10/site-packages/lightning/pytorch/callbacks/model_checkpoint.py", line 390, in _save_checkpoint
+    trainer.save_checkpoint(filepath, self.save_weights_only)
+  File "/opt/conda/lib/python3.10/site-packages/lightning/pytorch/trainer/trainer.py", line 1365, in save_checkpoint
+    self.strategy.save_checkpoint(checkpoint, filepath, storage_options=storage_options)
+  File "/opt/conda/lib/python3.10/site-packages/lightning/pytorch/strategies/strategy.py", line 490, in save_checkpoint
+    self.checkpoint_io.save_checkpoint(checkpoint, filepath, storage_options=storage_options)
+  File "/opt/conda/lib/python3.10/site-packages/lightning/fabric/plugins/io/torch_io.py", line 58, in save_checkpoint
+    _atomic_save(checkpoint, path)
+  File "/opt/conda/lib/python3.10/site-packages/lightning/fabric/utilities/cloud_io.py", line 90, in _atomic_save
+    f.write(bytesbuffer.getvalue())
+  File "/opt/conda/lib/python3.10/site-packages/fsspec/implementations/local.py", line 373, in write
+    return self.f.write(*args, **kwargs)
+OSError: [Errno 28] No space left on device
+[2024-10-22 01:31:05,792][matcha.utils.utils][INFO] - Output dir: /workspace/Matcha-TTS/logs/train/ljspeech/runs/2024-10-19_19-32-03