adding sepformer for wham

.gitattributes

@@ -1,16 +1 @@
-*.bin.* filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tar.gz filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text

CKPT.yaml

@@ -0,0 +1,4 @@
+# yamllint disable
+end-of-epoch: true
+si-snr: -12.183298104639045
+unixtime: 1615254590.2154887

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 sha256:85daaf6f7055cd5736287faed9603d712920092c4f8fd0097ec3b650bf27530e
+size 3

dataloader-TRAIN.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:876c9b16254e157d1eb645390dcfae6f29b9d3cd394e73a91de8ee5d0e67ee43
+size 5

decoder.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a06998d188f9fa0cb79915dc855aac4737c41392488b11d500b453000f4dfa
+size 17272

encoder.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33283041ba9a4cc292bc31ea14b1bfccad8304be822480571eaf95f9ccb0301
+size 17272

hyperparams.yaml

@@ -0,0 +1,177 @@
+# Generated 2021-03-09 from:
+# /home/mila/s/subakany/speechbrain_new/recipes/WSJ0Mix/separation/train/hparams/sepformer-wham.yaml
+# yamllint disable
+# ################################
+# Model: SepFormer for source separation
+# https://arxiv.org/abs/2010.13154
+#
+# Dataset : WSJ0-2mix and WSJ0-3mix
+# ################################
+# 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
+# needs to end with wham_reverb for the whamr dataset
+data_folder: /network/tmp1/subakany/wham_original
+
+# the path for wsj0/si_tr_s/ folder -- only needed if dynamic mixing is used
+# e.g. /yourpath/wsj0-processed/si_tr_s/
+wsj0_tr: /yourpath/wsj0-processed/si_tr_s/
+
+experiment_name: sepformer-wham
+output_folder: results/sepformer-wham/1234
+train_log: results/sepformer-wham/1234/train_log.txt
+save_folder: results/sepformer-wham/1234/save
+
+# the file names should start with whamr instead of whamorg
+train_data: results/sepformer-wham/1234/save/whamorg_tr.csv
+valid_data: results/sepformer-wham/1234/save/whamorg_cv.csv
+test_data: results/sepformer-wham/1234/save/whamorg_tt.csv
+skip_prep: false
+
+
+# Experiment params
+auto_mix_prec: false # Set it to True for mixed precision
+test_only: false
+num_spks: 2 # 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: false
+
+# 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: 2
+  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/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/1234/train_log.txt
+
+pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
+  loadables:
+    masknet: !ref <MaskNet>
+    encoder: !ref <Encoder>
+    decoder: !ref <Decoder>

lr_scheduler.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b16ecb0ad4a0d1cdfa31c45f79d74cbc35e283bf4a1bfdccac64bff1ab04cb6c
+size 1519

masknet.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f058bffbc94d3ac3fb2481239b9eda589cb53484d312714180c98ae5fee8bbf3
+size 113112646

optimizer.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4b60e4ed1f7cd399fe23556d4dfa5fe3e1f09904f04968bb84cad2936ce063d
+size 205694713