wavlm_partly_frozen.yaml

# ################################
# Model: wav2vec2 + DNN + CTC
# Augmentation: SpecAugment
# Authors: Sung-Lin Yeh 2021
# ################################

# Seed needs to be set at top of yaml, before objects with parameters are made
seed: 1986
__set_seed: !apply:torch.manual_seed [!ref <seed>]
output_folder: partly_frozen_splitted_wavlm/1986/
wer_file: !ref <output_folder>/wer.txt
save_folder: !ref <output_folder>/save
train_log: !ref <output_folder>/train_log.txt

# URL for the biggest Fairseq english wav2vec2 model.

# Data files
data_folder: /gpfsscratch/rech/nou/uzn19yk/Libri/LibriSpeech/ # e,g./path/to/LibriSpeech
# noise/ris dataset will automatically be downloaded
data_folder_rirs: !ref <data_folder>
train_splits: ["train-clean-100"]
dev_splits: ["dev-clean"]
test_splits: ["test-clean", "test-other"]
skip_prep: False
ckpt_interval_minutes: 25 # save checkpoint every N min
csv_folder: /gpfsstore/rech/nou/uzn19yk/iwslt/splitted_clean_tunisian_csvs/
train_csv: test_salah_local.csv
valid_csv: test_salah_local.csv
test_csv:
   - test_salah_local.csv

# Training parameters
number_of_epochs: 12
lr: 1
lr_wav2vec: 0.0001
sorting: ascending
auto_mix_prec: False
sample_rate: 16000

avoid_if_longer_than: 10
# With data_parallel batch_size is split into N jobs
# With DDP batch_size is multiplied by N jobs
# Must be 3 per GPU to fit 32GB of VRAM
batch_size: 1
test_batch_size: 1

# Dataloader options
train_dataloader_opts:
   batch_size: !ref <batch_size>

valid_dataloader_opts:
   batch_size: !ref <batch_size>

test_dataloader_opts:
   batch_size: !ref <test_batch_size>

# Model parameters
activation: !name:torch.nn.LeakyReLU
dnn_layers: 2
dnn_neurons: 1024
freeze_wav2vec: False

# Outputs
output_neurons: 41  # BPE size, index(blank/eos/bos) = 0

# Decoding parameters
blank_index: 0
bos_index: 1
eos_index: 2

#
# Functions and classes
#
epoch_counter: !new:speechbrain.utils.epoch_loop.EpochCounter
   limit: !ref <number_of_epochs>

augmentation: !new:speechbrain.lobes.augment.TimeDomainSpecAugment
   sample_rate: !ref <sample_rate>
   speeds: [95, 100, 105]

enc: !new:speechbrain.lobes.models.VanillaNN.VanillaNN
   input_shape: [null, null, 1024]
   activation: !ref <activation>
   dnn_blocks: !ref <dnn_layers>
   dnn_neurons: !ref <dnn_neurons>

wav2vec2: !new:speechbrain.lobes.models.huggingface_wav2vec.HuggingFaceWav2Vec2
   source: microsoft/wavlm-large
   output_norm: True
   freeze: False
   freeze_feature_extractor: True
   save_path: !ref <save_folder>/wav2vec2_hubert_checkpoint

#####
# Uncomment this block if you prefer to use a Fairseq pretrained model instead
# of a HuggingFace one. Here, we provide an URL that is obtained from the
# Fairseq github for the multilingual XLSR.
#
#wav2vec2_url: https://dl.fbaipublicfiles.com/fairseq/wav2vec/wav2vec_vox_960h_pl.pt
#wav2vec2: !new:speechbrain.lobes.models.fairseq_wav2vec.FairseqWav2Vec2
#    pretrained_path: !ref <wav2vec2_url>
#    output_norm: True
#    freeze: False
#    save_path: !ref <save_folder>/wav2vec2_checkpoint/model.pt

ctc_lin: !new:speechbrain.nnet.linear.Linear
   input_size: !ref <dnn_neurons>
   n_neurons: !ref <output_neurons>

log_softmax: !new:speechbrain.nnet.activations.Softmax
   apply_log: True

ctc_cost: !name:speechbrain.nnet.losses.ctc_loss
   blank_index: !ref <blank_index>

modules:
   wav2vec2: !ref <wav2vec2>
   enc: !ref <enc>
   ctc_lin: !ref <ctc_lin>

model: !new:torch.nn.ModuleList
   - [!ref <enc>, !ref <ctc_lin>]

model_opt_class: !name:torch.optim.Adadelta
   lr: !ref <lr>
   rho: 0.95
   eps: 1.e-8

wav2vec_opt_class: !name:torch.optim.Adam
   lr: !ref <lr_wav2vec>

lr_annealing_model: !new:speechbrain.nnet.schedulers.NewBobScheduler
   initial_value: !ref <lr>
   improvement_threshold: 0.0025
   annealing_factor: 0.8
   patient: 0

lr_annealing_wav2vec: !new:speechbrain.nnet.schedulers.NewBobScheduler
   initial_value: !ref <lr_wav2vec>
   improvement_threshold: 0.0025
   annealing_factor: 0.9
   patient: 0


checkpointer: !new:speechbrain.utils.checkpoints.Checkpointer
   checkpoints_dir: !ref <save_folder>
   recoverables:
      wav2vec2: !ref <wav2vec2>
      model: !ref <model>
      scheduler_model: !ref <lr_annealing_model>
      scheduler_wav2vec: !ref <lr_annealing_wav2vec>
      counter: !ref <epoch_counter>

train_logger: !new:speechbrain.utils.train_logger.FileTrainLogger
   save_file: !ref <train_log>

error_rate_computer: !name:speechbrain.utils.metric_stats.ErrorRateStats

cer_computer: !name:speechbrain.utils.metric_stats.ErrorRateStats
   split_tokens: True