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: Librispeech 960h
# Authors:  Jianyuan Zhong, Titouan Parcollet 2021
# ############################################################################

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

####################### Model parameters ###########################
# Transformer
d_model: 768
nhead: 8
num_encoder_layers: 12
num_decoder_layers: 6
d_ffn: 3072
transformer_dropout: 0.0
activation: !name:torch.nn.GELU
output_neurons: 5000
vocab_size: 5000

# 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
test_beam_size: 66
lm_weight: 0.60
ctc_weight_decode: 0.52

############################## models ################################

CNN: !new:speechbrain.lobes.models.convolution.ConvolutionFrontEnd
    input_shape: (8, 10, 80)
    num_blocks: 3
    num_layers_per_block: 1
    out_channels: (128, 256, 512)
    kernel_sizes: (3, 3, 1)
    strides: (2, 2, 1)
    residuals: (False, False, False)

Transformer: !new:speechbrain.lobes.models.transformer.TransformerASR.TransformerASR
    input_size: 10240
    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>
    normalize_before: False

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>

decoder: !new:speechbrain.decoders.S2STransformerBeamSearch
    modules: [!ref <Transformer>, !ref <seq_lin>, !ref <ctc_lin>]
    bos_index: !ref <bos_index>
    eos_index: !ref <eos_index>
    blank_index: !ref <blank_index>
    min_decode_ratio: !ref <min_decode_ratio>
    max_decode_ratio: !ref <max_decode_ratio>
    beam_size: !ref <test_beam_size>
    ctc_weight: !ref <ctc_weight_decode>
    lm_weight: !ref <lm_weight>
    lm_modules: !ref <lm_model>
    temperature: 1.15
    temperature_lm: 1.15
    using_eos_threshold: False
    length_normalization: True

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

normalize: !new:speechbrain.processing.features.InputNormalization
    norm_type: global
    update_until_epoch: 4

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

# This is the Transformer LM that is used according to the Huggingface repository
# Visit the HuggingFace model corresponding to the pretrained_lm_tokenizer_path
# For more details about the model!
# NB: It has to match the pre-trained TransformerLM!!
lm_model: !new:speechbrain.lobes.models.transformer.TransformerLM.TransformerLM
    vocab: 5000
    d_model: 768
    nhead: 12
    num_encoder_layers: 12
    num_decoder_layers: 0
    d_ffn: 3072
    dropout: 0.0
    activation: !name:torch.nn.GELU
    normalize_before: False

tokenizer: !new:sentencepiece.SentencePieceProcessor

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 <normalize>
    cnn: !ref <CNN>
    transformer_encoder: !ref <Tencoder>

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

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

# The pretrainer allows a mapping between pretrained files and instances that
# are declared in the yaml.
pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
   loadables:
      asr: !ref <asr_model>
      lm: !ref <lm_model>
      tokenizer: !ref <tokenizer>