Update hyperparams.yaml

hyperparams.yaml

@@ -1,92 +1,10 @@
-# Generated 2022-06-30 from:
-# /home/cem/Dropbox/speechbrain-1/recipes/WHAMandWHAMR/enhancement/yamls/sepformer-wham-16k.yaml
-# yamllint disable
 # ################################
-# Model: SepFormer for source separation
-# https://arxiv.org/abs/2010.13154
-#
+# Model: Pretrained SepFormer for speech enhancement
 # Dataset : WHAM!
 # ################################
-# Basic parameters
-# Seed needs to be set at top of yaml, before objects with parameters are made
-#
-seed: 1234
-__set_seed: !apply:torch.manual_seed [1234]
 
-# Data params
-
-# the data folder for the wham dataset
-# needs to end with wham_original for the wham dataset
-# respecting this convention effects the code functionality
-data_folder: /data2/wham_original/
-task: enhancement
-dereverberate: false
-
-# the path for wsj0/si_tr_s/ folder -- only needed if dynamic mixing is used
-# e.g. /yourpath/wsj0-processed/si_tr_s/
-## you need to convert the original wsj0 to 8k
-# you can do this conversion with ../meta/preprocess_dynamic_mixing.py
-base_folder_dm: /yourpath/wsj0-processed/si_tr_s/
-
-experiment_name: sepformer-wham-16k
-output_folder: results/sepformer-wham-16k/1234
-train_log: results/sepformer-wham-16k/1234/train_log.txt
-save_folder: results/sepformer-wham-16k/1234/save
-
-# the file names should start with whamr instead of whamorg
-train_data: results/sepformer-wham-16k/1234/save/whamorg_tr.csv
-valid_data: results/sepformer-wham-16k/1234/save/whamorg_cv.csv
-test_data: results/sepformer-wham-16k/1234/save/whamorg_tt.csv
-skip_prep: false
-
-
-# Experiment params
-auto_mix_prec: true # Set it to True for mixed precision
-test_only: true
 num_spks: 1 # set to 3 for wsj0-3mix
-noprogressbar: false
-save_audio: true # Save estimated sources on disk
 sample_rate: 16000
-n_audio_to_save: 20
-
-# Training parameters
-N_epochs: 200
-batch_size: 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: true
-# this is the length of sequences if we choose to limit
-# the signal length of training sequences
-training_signal_len: 64000
-
-# Set it to True to dynamically create mixtures at training time
-dynamic_mixing: false
-
-# Parameters for data augmentation
-use_wavedrop: false
-use_speedperturb: true
-use_rand_shift: false
-min_shift: -8000
-max_shift: 8000
-
-speedperturb: !new:speechbrain.lobes.augment.TimeDomainSpecAugment
-  perturb_prob: 1.0
-  drop_freq_prob: 0.0
-  drop_chunk_prob: 0.0
-  sample_rate: 16000
-  speeds: [95, 100, 105]
-
-wavedrop: !new:speechbrain.lobes.augment.TimeDomainSpecAugment
-  perturb_prob: 0.0
-  drop_freq_prob: 1.0
-  drop_chunk_prob: 1.0
-  sample_rate: 16000
-
-# loss thresholding -- this thresholds the training loss
-threshold_byloss: true
-threshold: -30
 
 # Encoder parameters
 N_encoder_out: 256
@@ -94,21 +12,11 @@ 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
-
 # Specifying the network
 Encoder: &id003 !new:speechbrain.lobes.models.dual_path.Encoder
   kernel_size: 16
   out_channels: 256
 
-
 SBtfintra: &id001 !new:speechbrain.lobes.models.dual_path.SBTransformerBlock
   num_layers: 8
   d_model: 256
@@ -128,7 +36,6 @@ SBtfinter: &id002 !new:speechbrain.lobes.models.dual_path.SBTransformerBlock
   norm_before: true
 
 MaskNet: &id005 !new:speechbrain.lobes.models.dual_path.Dual_Path_Model
-
   num_spks: 1
   in_channels: 256
   out_channels: 256
@@ -147,35 +54,10 @@ Decoder: &id004 !new:speechbrain.lobes.models.dual_path.Decoder
   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: 65
-
-epoch_counter: &id006 !new:speechbrain.utils.epoch_loop.EpochCounter
-  limit: 200
-
 modules:
   encoder: *id003
   decoder: *id004
   masknet: *id005
-checkpointer: !new:speechbrain.utils.checkpoints.Checkpointer
-  checkpoints_dir: results/sepformer-wham-16k/1234/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-wham-16k/1234/train_log.txt
 
 pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
   loadables: