hyperparams.yaml

# ################################
# Model: wav2vec2 + DNN + CTC
# Augmentation: SpecAugment
# Authors: 
# Sung-Lin Yeh 2021
# Pooneh Mousavi 2023
# ################################

# BPE parameters
token_type: unigram  # ["unigram", "bpe", "char"]
character_coverage: 1.0

# Model parameters
# activation: !name:torch.nn.LeakyReLU
dnn_neurons: 1024
wav2vec_output_dim: 1024
dropout: 0.15

sample_rate: 16000

wav2vec2_hub: facebook/wav2vec2-large-xlsr-53

# Outputs
output_neurons: 1000  # BPE size, index(blank/eos/bos) = 0

# Decoding parameters
# Be sure that the bos and eos index match with the BPEs ones
blank_index: 0
bos_index: 1
eos_index: 2

enc: !new:speechbrain.nnet.containers.Sequential
  input_shape: [null, null, !ref <wav2vec_output_dim>]
  linear1: !name:speechbrain.nnet.linear.Linear
    n_neurons: !ref <dnn_neurons>
    bias: True
  bn1: !name:speechbrain.nnet.normalization.BatchNorm1d
  activation: !new:torch.nn.LeakyReLU
  drop: !new:torch.nn.Dropout
    p: !ref <dropout>
  linear2: !name:speechbrain.nnet.linear.Linear
    n_neurons: !ref <dnn_neurons>
    bias: True
  bn2: !name:speechbrain.nnet.normalization.BatchNorm1d
  activation2: !new:torch.nn.LeakyReLU
  drop2: !new:torch.nn.Dropout
    p: !ref <dropout>
  linear3: !name:speechbrain.nnet.linear.Linear
    n_neurons: !ref <dnn_neurons>
    bias: True
  bn3: !name:speechbrain.nnet.normalization.BatchNorm1d
  activation3: !new:torch.nn.LeakyReLU

wav2vec2: !new:speechbrain.lobes.models.huggingface_transformers.wav2vec2.Wav2Vec2
  source: !ref <wav2vec2_hub>
  output_norm: True
  freeze: True
  save_path: wav2vec2_checkpoint

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>

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

tokenizer: !new:sentencepiece.SentencePieceProcessor

encoder: !new:speechbrain.nnet.containers.LengthsCapableSequential
    wav2vec2: !ref <wav2vec2>
    enc: !ref <enc>
    ctc_lin: !ref <ctc_lin>
    log_softmax: !ref <log_softmax>

modules:
  encoder: !ref <encoder>

decoding_function: !name:speechbrain.decoders.ctc_greedy_decode
    blank_id: !ref <blank_index>

pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
   loadables:
      wav2vec2: !ref <wav2vec2>
      asr: !ref <asr_model>
      tokenizer: !ref <tokenizer>