hyperparams.yaml

# ################################
# Model: wav2vec2 + DNN + CTC/Attention
# Augmentation: SpecAugment
# Authors: Titouan Parcollet 2021
# ################################

sample_rate: 16000
wav2vec2_hub: facebook/wav2vec2-large-it-voxpopuli

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

# Model parameters
activation: !name:torch.nn.LeakyReLU
dnn_layers: 2
dnn_neurons: 1024
emb_size: 128
dec_neurons: 1024

# Outputs
output_neurons: 500  # 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
min_decode_ratio: 0.0
max_decode_ratio: 1.0
beam_size: 80
eos_threshold: 1.5
using_max_attn_shift: True
max_attn_shift: 140
ctc_weight_decode: 0.0
temperature: 1.50

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: !ref <wav2vec2_hub>
    output_norm: True
    freeze: True
    pretrain: False
    save_path: model_checkpoints

emb: !new:speechbrain.nnet.embedding.Embedding
    num_embeddings: !ref <output_neurons>
    embedding_dim: !ref <emb_size>

dec: !new:speechbrain.nnet.RNN.AttentionalRNNDecoder
    enc_dim: !ref <dnn_neurons>
    input_size: !ref <emb_size>
    rnn_type: gru
    attn_type: location
    hidden_size: 1024
    attn_dim: 1024
    num_layers: 1
    scaling: 1.0
    channels: 10
    kernel_size: 100
    re_init: True
    dropout: 0.15

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

seq_lin: !new:speechbrain.nnet.linear.Linear
    input_size: !ref <dec_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>

seq_cost: !name:speechbrain.nnet.losses.nll_loss
    label_smoothing: 0.1

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

tokenizer: !new:sentencepiece.SentencePieceProcessor

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

decoder: !new:speechbrain.decoders.S2SRNNBeamSearcher
    embedding: !ref <emb>
    decoder: !ref <dec>
    linear: !ref <seq_lin>
    ctc_linear: !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 <beam_size>
    eos_threshold: !ref <eos_threshold>
    using_max_attn_shift: !ref <using_max_attn_shift>
    max_attn_shift: !ref <max_attn_shift>
    temperature: !ref <temperature>

modules:
    encoder: !ref <encoder>
    decoder: !ref <decoder>

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