initial commit

.gitattributes

@@ -25,3 +25,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+masknet.ckpt filter=lfs diff=lfs merge=lfs -text
+optimizer.ckpt filter=lfs diff=lfs merge=lfs -text
+brain.ckpt filter=lfs diff=lfs merge=lfs -text
+counter.ckpt filter=lfs diff=lfs merge=lfs -text
+decoder.ckpt filter=lfs diff=lfs merge=lfs -text
+encoder.ckpt filter=lfs diff=lfs merge=lfs -text
+lr_scheduler.ckpt filter=lfs diff=lfs merge=lfs -text

CKPT.yaml

@@ -0,0 +1,4 @@
+# yamllint disable
+end-of-epoch: true
+si-snr: -15.359142046070115
+unixtime: 1638387953.7461503

brain.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e24193f36931b7f57932532efbdcf64971f42732383ba6808825f77db258f6
+size 28

counter.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a699905c02619370bcf9207f5a477c3d67130ca71ec6f750e07fe8d510b084
+size 3

decoder.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4703b15d23ad5dd4c9b6b93b09539cf0048ba2e58a36c71a62fb860d5b0d343f
+size 17272

encoder.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c6b3e53a4061b81b7b0abf6a7faac8ee9714e0509a49ac60d249488e347430c
+size 17272

hyperparams.yaml

@@ -0,0 +1,175 @@
+# Generated 2021-12-01 from:
+# /home/mila/s/subakany/speechbrain-soundskrit/recipes/WHAMandWHAMR/enhancement/hparams/sepformer-wham.yaml
+# yamllint disable
+# ################################
+# Model: SepFormer for source separation
+# https://arxiv.org/abs/2010.13154
+#
+# 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: /network/tmp1/subakany/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 the script ../meta/preprocess_dynamic_mixing.py
+base_folder_dm: /network/tmp1/subakany/wsj0-processed/si_tr_s/
+
+experiment_name: sepformer-wham-enhancement
+output_folder: results/sepformer-wham-enhancement/1234
+train_log: results/sepformer-wham-enhancement/1234/train_log.txt
+save_folder: results/sepformer-wham-enhancement/1234/save
+
+# the file names should start with whamr instead of whamorg
+train_data: results/sepformer-wham-enhancement/1234/save/whamorg_tr.csv
+valid_data: results/sepformer-wham-enhancement/1234/save/whamorg_cv.csv
+test_data: results/sepformer-wham-enhancement/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
+progressbar: true
+save_audio: false # Save estimated sources on disk
+sample_rate: 8000
+
+# 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: false
+# this is the length of sequences if we choose to limit
+# the signal length of training sequences
+training_signal_len: 32000000
+
+# Set it to True to dynamically create mixtures at training time
+dynamic_mixing: true
+
+# Parameters for data augmentation
+use_wavedrop: false
+use_speedperturb: true
+use_speedperturb_sameforeachsource: false
+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: 8000
+  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: 8000
+
+# loss thresholding -- this thresholds the training loss
+threshold_byloss: true
+threshold: -30
+
+# Encoder parameters
+N_encoder_out: 256
+out_channels: 256
+kernel_size: 16
+kernel_stride: 8
+
+# Dataloader options
+dataloader_opts:
+  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
+  nhead: 8
+  d_ffn: 1024
+  dropout: 0
+  use_positional_encoding: true
+  norm_before: true
+
+SBtfinter: &id002 !new:speechbrain.lobes.models.dual_path.SBTransformerBlock
+  num_layers: 8
+  d_model: 256
+  nhead: 8
+  d_ffn: 1024
+  dropout: 0
+  use_positional_encoding: true
+  norm_before: true
+
+MaskNet: &id005 !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
+  norm: ln
+  linear_layer_after_inter_intra: false
+  skip_around_intra: true
+
+Decoder: &id004 !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: 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-enhancement/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-enhancement/1234/train_log.txt

lr_scheduler.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38d5d2d95d97c05f614716f700a35ac53b1a117d96c1a89ea8e2b7b4ab8ebb1b
+size 1583

masknet.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:111312d682aee6b72610b83edc0dcf253d7a62f745136cd2828113fb75fbb6e4
+size 112849478

optimizer.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c17d266b227ee5e2a9b09d1c87d40ebc93c6883e32c1541e7d6605c9890d2373
+size 205168377