simplified hyperparams.yaml and adding hyperparams_train.yaml

hyperparams.yaml

@@ -1,128 +1,17 @@
-# Generated 2021-09-17 from:
-# /home/mila/s/subakany/speechbrain_new/recipes/WSJ0Mix/separation/snrestimator_yamls/timedom_convnet_whamr_v2_stnorm_manyseparators.yaml
-# yamllint disable
 # ################################
-# Model: SepFormer for source separation
-# https://arxiv.org/abs/2010.13154
-# Dataset : WSJ0-2mix and WSJ0-3mix
+# Model: Neural SI-SNR Estimator with Pool training strategy (https://arxiv.org/pdf/2110.10812.pdf)
+# Dataset : LibriMix and WHAMR!
 # ################################
-#
-# 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
-
-# e.g. '/yourpath/wsj0-mix/2speakers'
-# end with 2speakers for wsj0-2mix or 3speakers for wsj0-3mix
-data_folder: /miniscratch/subakany/LibriMixData_new/Libri2Mix/
-
-# 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: /miniscratch/subakany/LibriMixData_new/LibriSpeech/train-clean-360_processed/
-rir_path: /miniscratch/subakany/whamr_rirs_wav
-
-experiment_name: snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators
-output_folder: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234
-train_log: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/train_log.txt
-save_folder: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/save
-train_data: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/save/libri2mix_train-360.csv
-valid_data: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/save/libri2mix_dev.csv
-test_data: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/save/libri2mix_test.csv
-
-wsj_data_folder: /network/tmp1/subakany/wham_original
-train_wsj_data: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/save/wham_tr.csv
-test_wsj_data: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/save/wham_tt.csv
-base_folder_dm_whamr: /network/tmp1/subakany/wsj0-processed/si_tr_s
-use_whamr_train: true
-whamr_proportion: 0.6
-
-test_onwsj: false
-
-skip_prep: false
-
-ckpt_interval_minutes: 60
-
-# 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: 0.0001
-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
-use_wham_noise: true
-use_reverb_augment: 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: 0
-
-
 # Specifying the network
 
 snrmin: 0
 snrmax: 10
-out_n_neurons: 16
 use_snr_compression: true
 separation_norm_type: stnorm
 
-# compute_features: !new:speechbrain.lobes.features.Fbank
-#     n_mels: !ref <n_mels>
-#     left_frames: 0
-#     right_frames: 0
-#     deltas: False
-
 latent_dim: 128
 n_inp: 256
 encoder: &id006 !new:speechbrain.nnet.containers.Sequential
@@ -169,26 +58,7 @@ encoder: &id006 !new:speechbrain.nnet.containers.Sequential
 
 stat_pooling: !new:speechbrain.nnet.pooling.StatisticsPooling
 
-
-        # classifier_enc: !new:speechbrain.lobes.models.ECAPA_TDNN.ECAPA_TDNN
-        #     input_size: !ref <n_inp>
-        #     channels: [1024, 1024, 1024, 1024, 3072]
-        #     kernel_sizes: [5, 3, 3, 3, 1]
-        #     dilations: [1, 2, 3, 4, 1]
-        #     attention_channels: 128
-        #     lin_neurons: 192
-
-#classifier_out: !new:speechbrain.lobes.models.ECAPA_TDNN.Classifier
-#    input_size: 192
-#    out_neurons: !ref <out_n_neurons>
-#
-# classifier_out: !new:speechbrain.nnet.linear.Linear
-#     input_size: 256
-#     n_neurons: 1
-
 encoder_out: &id007 !new:speechbrain.nnet.containers.Sequential
-        # lr_scheduler: !ref <lr_scheduler>
-
   input_shape: [!!null '', 256]
   layer1: !new:speechbrain.nnet.linear.Linear
     input_size: 256
@@ -199,38 +69,9 @@ encoder_out: &id007 !new:speechbrain.nnet.containers.Sequential
     n_neurons: 1
   sigm: !new:torch.nn.Sigmoid
 
-
-
-classifier_loss: !new:torch.nn.CrossEntropyLoss
-
-optimizer: !name:torch.optim.Adam
-  lr: 0.0001
-  weight_decay: 0
-
-loss: !name:speechbrain.nnet.losses.get_si_snr_with_pitwrapper
-
-lr_scheduler: !new:speechbrain.nnet.schedulers.ReduceLROnPlateau
-  factor: 0.5
-  patience: 2
-  dont_halve_until_epoch: 95
-
-epoch_counter: &id008 !new:speechbrain.utils.epoch_loop.EpochCounter
-  limit: 200
-
 modules:
   encoder: *id006
   encoder_out: *id007
-checkpointer: !new:speechbrain.utils.checkpoints.Checkpointer
-  checkpoints_dir: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/save
-  recoverables:
-    counter: *id008
-    encoder: *id006
-    encoder_out: *id007
-train_logger: !new:speechbrain.utils.train_logger.FileTrainLogger
-  save_file: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/train_log.txt
-
-num_separators_per_model: 3
-separator_base_folder: /home/mila/s/subakany/speechbrain_new/recipes/WHAMandWHAMR/separation/results/
 
 pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
     loadables:

hyperparams_training.yaml

@@ -0,0 +1,234 @@
+# ################################
+# Model: Neural SI-SNR Estimator with Pool training strategy (https://arxiv.org/pdf/2110.10812.pdf)
+# Dataset : LibriMix and WHAMR!
+# ################################
+#
+# 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
+
+# e.g. '/yourpath/wsj0-mix/2speakers'
+# end with 2speakers for wsj0-2mix or 3speakers for wsj0-3mix
+data_folder: /miniscratch/subakany/LibriMixData_new/Libri2Mix/
+
+# 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: /miniscratch/subakany/LibriMixData_new/LibriSpeech/train-clean-360_processed/
+rir_path: /miniscratch/subakany/whamr_rirs_wav
+
+experiment_name: snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators
+output_folder: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234
+train_log: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/train_log.txt
+save_folder: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/save
+train_data: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/save/libri2mix_train-360.csv
+valid_data: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/save/libri2mix_dev.csv
+test_data: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/save/libri2mix_test.csv
+
+wsj_data_folder: /network/tmp1/subakany/wham_original
+train_wsj_data: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/save/wham_tr.csv
+test_wsj_data: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/save/wham_tt.csv
+base_folder_dm_whamr: /network/tmp1/subakany/wsj0-processed/si_tr_s
+use_whamr_train: true
+whamr_proportion: 0.6
+
+test_onwsj: false
+
+skip_prep: false
+
+ckpt_interval_minutes: 60
+
+# 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: 0.0001
+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
+use_wham_noise: true
+use_reverb_augment: 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: 0
+
+
+# Specifying the network
+
+snrmin: 0
+snrmax: 10
+out_n_neurons: 16
+use_snr_compression: true
+separation_norm_type: stnorm
+
+# compute_features: !new:speechbrain.lobes.features.Fbank
+#     n_mels: !ref <n_mels>
+#     left_frames: 0
+#     right_frames: 0
+#     deltas: False
+
+latent_dim: 128
+n_inp: 256
+encoder: &id006 !new:speechbrain.nnet.containers.Sequential
+  input_shape: [!!null '', 2, !!null '']
+  cnn1: !new:speechbrain.nnet.CNN.Conv1d
+    in_channels: 2
+    kernel_size: 4
+    out_channels: 128
+    stride: 1
+    skip_transpose: true
+    padding: valid
+  relu1: !new:torch.nn.ReLU
+  cnn2: !new:speechbrain.nnet.CNN.Conv1d
+    in_channels: 128
+    kernel_size: 4
+    out_channels: 128
+    stride: 2
+    skip_transpose: true
+    padding: valid
+  relu2: !new:torch.nn.ReLU
+  cnn3: !new:speechbrain.nnet.CNN.Conv1d
+    in_channels: 128
+    kernel_size: 4
+    out_channels: 128
+    stride: 2
+    skip_transpose: true
+    padding: valid
+  relu3: !new:torch.nn.ReLU
+  cnn4: !new:speechbrain.nnet.CNN.Conv1d
+    in_channels: 128
+    kernel_size: 4
+    out_channels: 128
+    stride: 2
+    skip_transpose: true
+    padding: valid
+  relu4: !new:torch.nn.ReLU
+  cnn5: !new:speechbrain.nnet.CNN.Conv1d
+    in_channels: 128
+    kernel_size: 4
+    out_channels: 128
+    stride: 2
+    skip_transpose: true
+    padding: valid
+
+stat_pooling: !new:speechbrain.nnet.pooling.StatisticsPooling
+
+
+        # classifier_enc: !new:speechbrain.lobes.models.ECAPA_TDNN.ECAPA_TDNN
+        #     input_size: !ref <n_inp>
+        #     channels: [1024, 1024, 1024, 1024, 3072]
+        #     kernel_sizes: [5, 3, 3, 3, 1]
+        #     dilations: [1, 2, 3, 4, 1]
+        #     attention_channels: 128
+        #     lin_neurons: 192
+
+#classifier_out: !new:speechbrain.lobes.models.ECAPA_TDNN.Classifier
+#    input_size: 192
+#    out_neurons: !ref <out_n_neurons>
+#
+# classifier_out: !new:speechbrain.nnet.linear.Linear
+#     input_size: 256
+#     n_neurons: 1
+
+encoder_out: &id007 !new:speechbrain.nnet.containers.Sequential
+        # lr_scheduler: !ref <lr_scheduler>
+
+  input_shape: [!!null '', 256]
+  layer1: !new:speechbrain.nnet.linear.Linear
+    input_size: 256
+    n_neurons: 256
+  relu: !new:torch.nn.ReLU
+  layer2: !new:speechbrain.nnet.linear.Linear
+    input_size: 256
+    n_neurons: 1
+  sigm: !new:torch.nn.Sigmoid
+
+
+
+classifier_loss: !new:torch.nn.CrossEntropyLoss
+
+optimizer: !name:torch.optim.Adam
+  lr: 0.0001
+  weight_decay: 0
+
+loss: !name:speechbrain.nnet.losses.get_si_snr_with_pitwrapper
+
+lr_scheduler: !new:speechbrain.nnet.schedulers.ReduceLROnPlateau
+  factor: 0.5
+  patience: 2
+  dont_halve_until_epoch: 95
+
+epoch_counter: &id008 !new:speechbrain.utils.epoch_loop.EpochCounter
+  limit: 200
+
+modules:
+  encoder: *id006
+  encoder_out: *id007
+checkpointer: !new:speechbrain.utils.checkpoints.Checkpointer
+  checkpoints_dir: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/save
+  recoverables:
+    counter: *id008
+    encoder: *id006
+    encoder_out: *id007
+train_logger: !new:speechbrain.utils.train_logger.FileTrainLogger
+  save_file: results/snrtrain-timedomain-sbpooling-wwhamr-lessstride-stnorm-manyseparators/1234/train_log.txt
+
+num_separators_per_model: 3
+separator_base_folder: /home/mila/s/subakany/speechbrain_new/recipes/WHAMandWHAMR/separation/results/
+
+pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
+    loadables:
+        encoder: !ref <encoder>
+        encoder_out: !ref <encoder_out>