hyperparams.yaml

# ############################################################################
# Model: E2E ASR with Transformer
# Encoder: Transformer Encoder
# Decoder: Transformer Decoder + (CTC/ATT joint) beamsearch + TransformerLM
# Tokens: unigram
# losses: CTC + KLdiv (Label Smoothing loss)
# Training: Switchboard
# Authors:  Jianyuan Zhong, Titouan Parcollet, Samuele Cornell, Dominik Wagner
# ############################################################################

# Feature parameters
sample_rate: 16000
n_fft: 400
n_mels: 80

####################### Model parameters  ###########################
# Transformer
transformer_input_size: 1280
d_model: 256
nhead: 4
num_encoder_layers: 12
num_decoder_layers: 6
d_ffn: 2048
transformer_dropout: 0.1
activation: !name:torch.nn.GELU
output_neurons: 2000

# Outputs
blank_index: 0
label_smoothing: 0.1
pad_index: 0
bos_index: 1
eos_index: 2
# unk_index: 0

# Decoding parameters
min_decode_ratio: 0.0
max_decode_ratio: 1.0
valid_search_interval: 10
valid_beam_size: 10
lm_weight: 0.30
test_beam_size: 60
ctc_weight_decode: 0.30
temperature: 1.0
temperature_lm: 1.0
using_eos_threshold: False
eos_threshold: 1.5
length_normalization: True
using_max_attn_shift: False
max_attn_shift: 30

CNN: !new:speechbrain.lobes.models.convolution.ConvolutionFrontEnd
  input_shape: (8, 10, 80)
  num_blocks: 3
  num_layers_per_block: 1
  out_channels: (64, 64, 64)
  kernel_sizes: (5, 5, 1)
  strides: (2, 2, 1)
  residuals: (False, False, True)

Transformer: !new:speechbrain.lobes.models.transformer.TransformerASR.TransformerASR # yamllint disable-line rule:line-length
  input_size: !ref <transformer_input_size>
  tgt_vocab: !ref <output_neurons>
  d_model: !ref <d_model>
  nhead: !ref <nhead>
  num_encoder_layers: !ref <num_encoder_layers>
  num_decoder_layers: !ref <num_decoder_layers>
  d_ffn: !ref <d_ffn>
  dropout: !ref <transformer_dropout>
  activation: !ref <activation>
  encoder_module: transformer
  attention_type: regularMHA
  normalize_before: True
  causal: False

lm_model: !new:speechbrain.lobes.models.transformer.TransformerLM.TransformerLM # yamllint disable-line rule:line-length
  vocab: !ref <output_neurons>
  d_model: 264
  d_embedding: 128
  nhead: 12
  num_encoder_layers: 12
  num_decoder_layers: 0
  d_ffn: 1024
  dropout: 0.1
  activation: !name:torch.nn.ReLU
  normalize_before: False

tokenizer: !new:sentencepiece.SentencePieceProcessor

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

seq_lin: !new:speechbrain.nnet.linear.Linear
  input_size: !ref <d_model>
  n_neurons: !ref <output_neurons>

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

log_softmax: !new:torch.nn.LogSoftmax
  dim: -1

normalizer: !new:speechbrain.processing.features.InputNormalization
    norm_type: global

compute_features: !new:speechbrain.lobes.features.Fbank
  sample_rate: !ref <sample_rate>
  n_fft: !ref <n_fft>
  n_mels: !ref <n_mels>

Tencoder: !new:speechbrain.lobes.models.transformer.TransformerASR.EncoderWrapper
    transformer: !ref <Transformer>

encoder: !new:speechbrain.nnet.containers.LengthsCapableSequential
    input_shape: [null, null, !ref <n_mels>]
    compute_features: !ref <compute_features>
    normalize: !ref <normalizer>
    cnn: !ref <CNN>
    transformer_encoder: !ref <Tencoder>

transformerlm_scorer: !new:speechbrain.decoders.scorer.TransformerLMScorer
   language_model: !ref <lm_model>
   temperature: !ref <temperature_lm>
   
ctc_scorer: !new:speechbrain.decoders.scorer.CTCScorer
    eos_index: !ref <eos_index>
    blank_index: !ref <blank_index>
    ctc_fc: !ref <ctc_lin>
    
scorer: !new:speechbrain.decoders.scorer.ScorerBuilder
    full_scorers: [!ref <transformerlm_scorer>, !ref <ctc_scorer>]
    weights:
        transformerlm: !ref <lm_weight>
        ctc: !ref <ctc_weight_decode>
        
decoder: !new:speechbrain.decoders.S2STransformerBeamSearcher
  modules: [!ref <Transformer>, !ref <seq_lin>]
  bos_index: !ref <bos_index>
  eos_index: !ref <eos_index>
  min_decode_ratio: !ref <min_decode_ratio>
  max_decode_ratio: !ref <max_decode_ratio>
  beam_size: !ref <test_beam_size>
  temperature: !ref <temperature>
  using_eos_threshold: !ref <using_eos_threshold>
  eos_threshold: !ref <eos_threshold>
  length_normalization: !ref <length_normalization>
  using_max_attn_shift: !ref <using_max_attn_shift>
  max_attn_shift: !ref <max_attn_shift>
  scorer: !ref <scorer>

modules:
   compute_features: !ref <compute_features>
   normalizer: !ref <normalizer>
   pre_transformer: !ref <CNN>
   transformer: !ref <Transformer>
   asr_model: !ref <asr_model>
   lm_model: !ref <lm_model>
   encoder: !ref <encoder>
   decoder: !ref <decoder>

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