refactoring file organization

.gitattributes

@@ -25,3 +25,4 @@ 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
+*.ckpt filter=lfs diff=lfs merge=lfs -text

brain.ckpt

@@ -1,2 +1,3 @@
-avg_train_loss: 0.0
-step: 0
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e24193f36931b7f57932532efbdcf64971f42732383ba6808825f77db258f6
+size 28

counter.ckpt

@@ -1 +1,3 @@
-14
+version https://git-lfs.github.com/spec/v1
+oid sha256:8527a891e224136950ff32ca212b45bc93f69fbb801c3b1ebedac52775f99e61
+size 2

sepformer1/decoder.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:308586da02de3c86af1a597eabf7613d96c12d558bc1ef82274a286ab18281c2
-size 17272

sepformer1/encoder.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4ba8d001c2b3fbd7cd034271448c0b51e6e7e4f33e9c0f6fc2fe80414ce9c42c
-size 17272

sepformer1/hyperparams.yaml

@@ -1,184 +0,0 @@
-# Generated 2021-09-23 from:
-# /home/mila/s/subakany/speechbrain_new/recipes/WHAMandWHAMR/separation/hparams/sepformer-whamr.yaml
-# yamllint disable
-# ################################
-# Model: SepFormer for source separation
-# https://arxiv.org/abs/2010.13154
-#
-# Dataset : WHAMR!
-# ################################
-# Basic parameters
-# Seed needs to be set at top of yaml, before objects with parameters are made
-#
-seed: 3
-__set_seed: !apply:torch.manual_seed [3]
-
-# Data params
-
-# the data folder for the wham dataset
-# data_folder needs to follow the format:  /yourpath/whamr.
-# make sure to use the name whamr at your top folder for the dataset!
-data_folder: /network/tmp1/subakany/whamr
-
-# 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-whamr
-output_folder: results/sepformer-whamr/3
-train_log: results/sepformer-whamr/3/train_log.txt
-save_folder: results/sepformer-whamr/3/save
-
-# the file names should start with whamr instead of whamorg
-train_data: results/sepformer-whamr/3/save/whamr_tr.csv
-valid_data: results/sepformer-whamr/3/save/whamr_cv.csv
-test_data: results/sepformer-whamr/3/save/whamr_tt.csv
-skip_prep: false
-
-# Experiment params
-auto_mix_prec: true # 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: true
-
-# Parameters for data augmentation
-
-# rir_path variable points to the directory of the room impulse responses
-# e.g. /miniscratch/subakany/rir_wavs
-# If the path does not exist, it is created automatically.
-rir_path: /miniscratch/subakany/whamr_rirs_wav
-
-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: 85
-
-epoch_counter: &id006 !new:speechbrain.utils.epoch_loop.EpochCounter
-  limit: 200
-
-modules:
-  encoder: *id003
-  decoder: *id004
-  masknet: *id005
-save_all_checkpoints: true
-checkpointer: !new:speechbrain.utils.checkpoints.Checkpointer
-  checkpoints_dir: results/sepformer-whamr/3/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-whamr/3/train_log.txt
-
-pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
-   loadables:
-       encoder: !ref <Encoder>
-       masknet: !ref <MaskNet>
-       decoder: !ref <Decoder>

sepformer1/masknet.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8e5772c0ed40c85a2ea12fa9c2bbf6fe5a247bec060d13e63e97db085340bb4c
-size 113112646