hyperparams cleanup

hyperparams.yaml

@@ -1,77 +1,12 @@
-# Generated 2023-06-20 from:
-# /netscratch/sagar/thesis/speechbrain/recipes/RescueSpeech/Enhancement/fine-tuning/hparams/sepformer_16k.yaml
-# yamllint disable
+
 # ################################
 # Model: SepFormer for source separation
 # https://arxiv.org/abs/2010.13154
-#
-# Author:  Sangeet Sagar 2022
 # Dataset : RescueSpeech
 # ################################
 
-# Basic parameters
-# Seed needs to be set at top of yaml, before objects with parameters are made
-seed: 8201
-__set_seed: !apply:torch.manual_seed [8201]
-experiment_name: sepformer-enhancement
-output_folder: results/sepformer-enhancement/8201
-train_log: results/sepformer-enhancement/8201/train_log.txt
-save_folder: results/sepformer-enhancement/8201/save
-
-# Dataset prep parameters
-data_folder: dataset/audio_sythesis/Task_enhancement/ # !PLACEHOLDER
-csv_dir: csv_files
-train_csv: csv_files/train.csv
-valid_csv: csv_files/dev.csv
-test_csv: csv_files/test.csv
-skip_prep: false
 sample_rate: 16000
-task: enhance
-
-dereverberate: false
-shuffle_train_data: true
-
-# Pretrained models
-pretrained_model_path: 
-  /netscratch/sagar/thesis/speechbrain/recipes/RescueSpeech/pre-trained/sepformer_dns_16k                      # !PLACEHOLDER # sepformer_dns_16k model
-
-# Basic parameters
-use_tensorboard: false
-tensorboard_logs: results/sepformer-enhancement/8201/logs/
-
-# Experiment params
-auto_mix_prec: true     # Set it to True for mixed precision
-test_only: false
 num_spks: 1
-noprogressbar: false
-save_audio: true        # Save estimated sources on disk
-downsample: false
-n_audio_to_save: 500
-
-# Training parameters
-N_epochs: 150
-batch_size: 1
-batch_size_test: 1
-lr: 0.00015
-clip_grad_norm: 5
-loss_upper_lim: 999999  # this is the upper limit for an acceptable loss
-# if True, the training sequences are cut to a specified length
-limit_training_signal_len: false
-# this is the length of sequences if we choose to limit
-# the signal length of training sequences
-training_signal_len: 32000
-ckpt_interval_minutes: 60
-
-# Parameters for data augmentation
-use_wavedrop: false
-use_speedperturb: true
-use_rand_shift: false
-min_shift: -8000
-max_shift: 8000
-
-# loss thresholding -- this thresholds the training loss
-threshold_byloss: true
-threshold: -30
 
 # Encoder parameters
 N_encoder_out: 256
@@ -79,25 +14,12 @@ out_channels: 256
 kernel_size: 16
 kernel_stride: 8
 
-# Dataloader options
-dataloader_opts:
-  batch_size: 1
-  num_workers: 3
-
-dataloader_opts_valid:
-  batch_size: 1
-  num_workers: 3
-
-dataloader_opts_test:
-  batch_size: 1
-  num_workers: 3
-
 # Specifying the network
-Encoder: &id003 !new:speechbrain.lobes.models.dual_path.Encoder
+Encoder: !new:speechbrain.lobes.models.dual_path.Encoder
   kernel_size: 16
   out_channels: 256
 
-SBtfintra: &id001 !new:speechbrain.lobes.models.dual_path.SBTransformerBlock
+SBtfintra: !new:speechbrain.lobes.models.dual_path.SBTransformerBlock
   num_layers: 8
   d_model: 256
   nhead: 8
@@ -106,7 +28,7 @@ SBtfintra: &id001 !new:speechbrain.lobes.models.dual_path.SBTransformerBlock
   use_positional_encoding: true
   norm_before: true
 
-SBtfinter: &id002 !new:speechbrain.lobes.models.dual_path.SBTransformerBlock
+SBtfinter: !new:speechbrain.lobes.models.dual_path.SBTransformerBlock
   num_layers: 8
   d_model: 256
   nhead: 8
@@ -115,58 +37,30 @@ SBtfinter: &id002 !new:speechbrain.lobes.models.dual_path.SBTransformerBlock
   use_positional_encoding: true
   norm_before: true
 
-MaskNet: &id005 !new:speechbrain.lobes.models.dual_path.Dual_Path_Model
-
+MaskNet: new:speechbrain.lobes.models.dual_path.Dual_Path_Model
   num_spks: 1
   in_channels: 256
   out_channels: 256
   num_layers: 2
   K: 250
-  intra_model: *id001
-  inter_model: *id002
+  intra_model: !ref <SBtfintra>
+  inter_model: !ref <SBtfinter>
   norm: ln
   linear_layer_after_inter_intra: false
   skip_around_intra: true
 
-Decoder: &id004 !new:speechbrain.lobes.models.dual_path.Decoder
+Decoder: !new:speechbrain.lobes.models.dual_path.Decoder
   in_channels: 256
   out_channels: 1
   kernel_size: 16
   stride: 8
   bias: false
 
-optimizer: !name:torch.optim.Adam
-  lr: 0.00015
-  weight_decay: 0
-
-loss: !name:speechbrain.nnet.losses.get_si_snr_with_pitwrapper
-
-lr_scheduler: &id007 !new:speechbrain.nnet.schedulers.ReduceLROnPlateau
-
-  factor: 0.5
-  patience: 2
-  dont_halve_until_epoch: 85
-
-epoch_counter: &id006 !new:speechbrain.utils.epoch_loop.EpochCounter
-  limit: 150
-
 modules:
-  encoder: *id003
-  decoder: *id004
-  masknet: *id005
-save_all_checkpoints: false
-checkpointer: !new:speechbrain.utils.checkpoints.Checkpointer
-  checkpoints_dir: results/sepformer-enhancement/8201/save
-  recoverables:
-    encoder: *id003
-    decoder: *id004
-    masknet: *id005
-    counter: *id006
-    lr_scheduler: *id007
-train_logger: !new:speechbrain.utils.train_logger.FileTrainLogger
-  save_file: results/sepformer-enhancement/8201/train_log.txt
-
-## Uncomment if you wish to fine-tune a pre-trained model.
+  encoder: !ref <Encoder>
+  decoder: !ref <Decoder>
+  masknet: !ref <MaskNet>
+ 
 pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
   loadables:
     encoder: !ref <Encoder>