pushing the sepformer wsj0-3mix model

.gitattributes

@@ -14,3 +14,10 @@
 *.pb filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth 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
+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

CKPT.yaml

@@ -0,0 +1,4 @@
+# yamllint disable
+end-of-epoch: true
+si-snr: -17.452686241187454
+unixtime: 1614493079.2818

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 sha256:8bcbb4c131df56f7c79066016241cc4bdf4e58db55c4f674e88b22365bd2e2ad
+size 3

decoder.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4744290ae39cee1c011bbb33e437ccf7b5b94c6c3b70fef595b6b7d53c32b0b7
+size 17202

encoder.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afdabc2f213c6391002088c0faade7253f62c1ad910c58b3c42a3147f3421451
+size 17267

hyperparams.yaml

@@ -0,0 +1,163 @@
+# Generated 2021-03-09 from:
+# /home/mila/s/subakany/speechbrain_new/recipes/WSJ0Mix/separation/yamls/dpt-3mix-17.yaml
+# yamllint disable
+# ################################
+# Model: SepFormer for source separation
+# https://arxiv.org/abs/2010.13154
+#
+# Dataset : WSJ0-mix
+# ################################
+# 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
+data_folder: /network/tmp1/subakany/wsj0-mix/3speakers   # wsj2mix or wsj3mix
+experiment_name: 17-augment-3mix-dm
+output_folder: results/17-augment-3mix-dm/1234
+train_log: results/17-augment-3mix-dm/1234/train_log.txt
+save_folder: results/17-augment-3mix-dm/1234/save
+train_data: results/17-augment-3mix-dm/1234/save/wsj_tr.csv
+valid_data: results/17-augment-3mix-dm/1234/save/wsj_cv.csv
+test_data: results/17-augment-3mix-dm/1234/save/wsj_tt.csv
+wsj0_tr: /network/tmp1/subakany/wsj0-processed/si_tr_s/
+skip_prep: false
+
+# Experiment params
+auto_mix_prec: true
+test_only: true
+num_spks: 3 # 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: 32000
+dynamic_mixing: regular
+
+# Augment parameters
+use_wavedrop: false
+use_speedperturb: true
+use_speedperturb_sameforeachsource: false
+use_rand_shift: false
+min_shift: -8000
+max_shift: 8000
+
+# Neural parameters
+N_encoder_out: 256
+out_channels: 256
+kernel_size: 16
+kernel_stride: 8
+
+threshold_byloss: true
+threshold: -30
+
+# Dataloader options
+dataloader_opts:
+  batch_size: 1
+  num_workers: 3
+
+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
+
+
+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: 3
+  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: 100
+
+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/17-augment-3mix-dm/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/17-augment-3mix-dm/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 sha256:4b399abc1f483ba137f394dc2ce4757f642de66584e0f3bb53602ab9af07ed17
+size 2223

masknet.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c11786f74723c8e7021f6c9769057724c5e6833d1ed0f09fc935adfcb8a0078
+size 113371626

optimizer.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f94ab3d414ef043530ddb2d55baf995ac55297b82f70538cf11e3e40e5fae9e
+size 206212823