Upload 2 files

config.yaml

@@ -1,146 +1,28 @@
-# pytorch_lightning==1.8.6
-seed_everything: 4444
-trainer:
-  logger:
-    class_path: pytorch_lightning.loggers.TensorBoardLogger
-    init_args:
-      save_dir: logs/
-      name: lightning_logs
-      version: null
-      log_graph: false
-      default_hp_metric: true
-      prefix: ''
-      sub_dir: null
-      logdir: null
-      comment: ''
-      purge_step: null
-      max_queue: 10
-      flush_secs: 120
-      filename_suffix: ''
-      write_to_disk: true
-      comet_config:
-        disabled: true
-  enable_checkpointing: true
-  callbacks:
-  - class_path: pytorch_lightning.callbacks.LearningRateMonitor
-    init_args:
-      logging_interval: null
-      log_momentum: false
-  - class_path: pytorch_lightning.callbacks.ModelSummary
-    init_args:
-      max_depth: 2
-  - class_path: pytorch_lightning.callbacks.ModelCheckpoint
-    init_args:
-      dirpath: null
-      filename: vocos_checkpoint_{epoch}_{step}_{val_loss:.4f}
-      monitor: val_loss
-      verbose: false
-      save_last: true
-      save_top_k: 3
-      save_weights_only: false
-      mode: min
-      auto_insert_metric_name: true
-      every_n_train_steps: null
-      train_time_interval: null
-      every_n_epochs: null
-      save_on_train_epoch_end: null
-  - class_path: vocos.helpers.GradNormCallback
-  default_root_dir: null
-  gradient_clip_val: null
-  gradient_clip_algorithm: null
-  num_nodes: 1
-  num_processes: null
-  devices:
-  - 0
-  - 1
-  - 2
-  gpus: null
-  auto_select_gpus: false
-  tpu_cores: null
-  ipus: null
-  enable_progress_bar: true
-  overfit_batches: 0.0
-  track_grad_norm: -1
-  check_val_every_n_epoch: 1
-  fast_dev_run: false
-  accumulate_grad_batches: null
-  max_epochs: null
-  min_epochs: null
-  max_steps: 2000000
-  min_steps: null
-  max_time: null
-  limit_train_batches: null
-  limit_val_batches: 100
-  limit_test_batches: null
-  limit_predict_batches: null
-  val_check_interval: null
-  log_every_n_steps: 100
-  accelerator: gpu
-  strategy: ddp
-  sync_batchnorm: false
-  precision: 32
-  enable_model_summary: true
-  num_sanity_val_steps: 2
-  resume_from_checkpoint: null
-  profiler: null
-  benchmark: null
-  deterministic: null
-  reload_dataloaders_every_n_epochs: 0
-  auto_lr_find: false
-  replace_sampler_ddp: true
-  detect_anomaly: false
-  auto_scale_batch_size: false
-  plugins: null
-  amp_backend: native
-  amp_level: null
-  move_metrics_to_cpu: false
-  multiple_trainloader_mode: max_size_cycle
-  inference_mode: true
-data:
-  class_path: vocos.dataset.VocosDataModule
+backbone:
+  class_path: vocos.models.VocosBackbone
   init_args:
-    train_params:
-      filelist_path: /data/umeiro0/datasets/librispeech/LibriSpeech/filelist.train
-      base_dir: /data/umeiro0/datasets/librispeech/LibriSpeech
-      sampling_rate: 16000
-      num_samples: 16000
-      batch_size: 32
-      num_workers: 8
-    val_params:
-      filelist_path: /data/umeiro0/datasets/librispeech/LibriSpeech/filelist.val
-      base_dir: /data/umeiro0/datasets/librispeech/LibriSpeech
-      sampling_rate: 16000
-      num_samples: 16000
-      batch_size: 16
-      num_workers: 8
-model:
-  class_path: vocos.experiment.VocosDACExp
+    adanorm_num_embeddings: null
+    dim: 384
+    input_channels: 1024
+    intermediate_dim: 1152
+    layer_scale_init_value: null
+    num_layers: 8
+decay_mel_coeff: false
+evaluate_periodicty: true
+evaluate_pesq: true
+evaluate_utmos: true
+feature_extractor:
+  class_path: vocos.feature_extractors.DACFeatures
+head:
+  class_path: vocos.heads.ISTFTHead
   init_args:
-    feature_extractor:
-      class_path: vocos.feature_extractors.DACFeatures
-    backbone:
-      class_path: vocos.models.VocosBackbone
-      init_args:
-        input_channels: 1024
-        dim: 384
-        intermediate_dim: 1152
-        num_layers: 8
-        layer_scale_init_value: null
-        adanorm_num_embeddings: null
-    head:
-      class_path: vocos.heads.ISTFTHead
-      init_args:
-        dim: 384
-        n_fft: 1280
-        hop_length: 320
-        padding: same
-    sample_rate: 16000
-    initial_learning_rate: 0.0005
-    num_warmup_steps: 0
-    mel_loss_coeff: 45.0
-    mrd_loss_coeff: 1.0
-    pretrain_mel_steps: 0
-    decay_mel_coeff: false
-    evaluate_utmos: true
-    evaluate_pesq: true
-    evaluate_periodicty: true
+    dim: 384
+    hop_length: 320
+    n_fft: 1280
+    padding: same
+initial_learning_rate: 0.0005
+mel_loss_coeff: 45.0
+mrd_loss_coeff: 1.0
+num_warmup_steps: 0
+pretrain_mel_steps: 0
+sample_rate: 16000

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b89183291b503f246227dd145947839400e7f509c12a70764967f2117bd24580
-size 508782458
+oid sha256:77faf1fde32ad5438b22eb9ba80e611876e4ff8bb744c067c71cfae9adc341ae
+size 338395542