|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
sample_rate: 16000 |
|
n_fft: 400 |
|
n_mels: 80 |
|
win_length: 25 |
|
n_time_mask: 7 |
|
|
|
|
|
|
|
d_model: 512 |
|
nhead: 8 |
|
num_encoder_layers: 18 |
|
num_decoder_layers: 6 |
|
csgu_linear_units: 3072 |
|
csgu_kernel_size: 31 |
|
transformer_dropout: 0.1 |
|
activation: !name:torch.nn.GELU |
|
output_neurons: 500 |
|
|
|
|
|
blank_index: 0 |
|
label_smoothing: 0.1 |
|
pad_index: 0 |
|
bos_index: 1 |
|
eos_index: 2 |
|
|
|
|
|
min_decode_ratio: 0.0 |
|
max_decode_ratio: 1.0 |
|
beam_size: 20 |
|
ctc_weight_decode: 0.3 |
|
|
|
|
|
|
|
CNN: !new:speechbrain.lobes.models.convolution.ConvolutionFrontEnd |
|
input_shape: (8, 10, 80) |
|
num_blocks: 2 |
|
num_layers_per_block: 1 |
|
out_channels: (64, 32) |
|
kernel_sizes: (3, 3) |
|
strides: (2, 2) |
|
residuals: (False, False) |
|
|
|
Transformer: !new:speechbrain.lobes.models.transformer.TransformerASR.TransformerASR |
|
input_size: 640 |
|
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> |
|
dropout: !ref <transformer_dropout> |
|
activation: !ref <activation> |
|
branchformer_activation: !ref <activation> |
|
encoder_module: branchformer |
|
csgu_linear_units: !ref <csgu_linear_units> |
|
kernel_size: !ref <csgu_kernel_size> |
|
attention_type: RelPosMHAXL |
|
normalize_before: True |
|
causal: 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 <beam_size> |
|
ctc_weight: !ref <ctc_weight_decode> |
|
temperature: 1.15 |
|
temperature_lm: 1.15 |
|
using_eos_threshold: False |
|
length_normalization: True |
|
|
|
log_softmax: !new:torch.nn.LogSoftmax |
|
dim: -1 |
|
|
|
normalizer: !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> |
|
win_length: !ref <win_length> |
|
n_mels: !ref <n_mels> |
|
|
|
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 <normalizer> |
|
cnn: !ref <CNN> |
|
transformer_encoder: !ref <Tencoder> |
|
|
|
model: !new:torch.nn.ModuleList |
|
- [!ref <CNN>, !ref <Transformer>, !ref <seq_lin>, !ref <ctc_lin>] |
|
|
|
modules: |
|
pre_transformer: !ref <CNN> |
|
transformer: !ref <Transformer> |
|
seq_lin: !ref <seq_lin> |
|
ctc_lin: !ref <ctc_lin> |
|
normalizer: !ref <normalizer> |
|
encoder: !ref <encoder> |
|
compute_features: !ref <compute_features> |
|
model: !ref <model> |
|
decoder: !ref <decoder> |
|
|
|
|
|
|
|
pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer |
|
loadables: |
|
normalizer: !ref <normalizer> |
|
model: !ref <model> |
|
tokenizer: !ref <tokenizer> |
