-
Notifications
You must be signed in to change notification settings - Fork 1.1k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'main' into xcsong-yaml
- Loading branch information
Showing
9 changed files
with
202 additions
and
30 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,91 @@ | ||
# network architecture | ||
# encoder related | ||
encoder: conformer | ||
encoder_conf: | ||
output_size: 256 # dimension of attention | ||
attention_heads: 4 | ||
linear_units: 2048 # the number of units of position-wise feed forward | ||
num_blocks: 12 # the number of encoder blocks | ||
dropout_rate: 0.1 | ||
positional_dropout_rate: 0.1 | ||
attention_dropout_rate: 0.1 | ||
input_layer: conv2d # encoder input type, you can chose conv2d, conv2d6 and conv2d8 | ||
normalize_before: true | ||
cnn_module_kernel: 8 | ||
use_cnn_module: True | ||
activation_type: 'swish' | ||
pos_enc_layer_type: 'rel_pos' | ||
selfattention_layer_type: 'rel_selfattn' | ||
causal: true | ||
use_dynamic_chunk: true | ||
cnn_module_norm: 'layer_norm' # using nn.LayerNorm makes model converge faster | ||
use_dynamic_left_chunk: false | ||
|
||
# decoder related | ||
decoder: bitransformer | ||
decoder_conf: | ||
attention_heads: 4 | ||
linear_units: 1024 | ||
num_blocks: 3 | ||
r_num_blocks: 3 | ||
dropout_rate: 0.1 | ||
positional_dropout_rate: 0.1 | ||
self_attention_dropout_rate: 0.1 | ||
src_attention_dropout_rate: 0.1 | ||
|
||
# hybrid CTC/attention | ||
model_conf: | ||
ctc_weight: 0.3 | ||
lsm_weight: 0.1 # label smoothing option | ||
length_normalized_loss: false | ||
reverse_weight: 0.3 | ||
apply_non_blank_embedding: true # warning: had better use a well trained model as init model | ||
|
||
dataset_conf: | ||
filter_conf: | ||
max_length: 40960 | ||
min_length: 0 | ||
token_max_length: 200 | ||
token_min_length: 1 | ||
resample_conf: | ||
resample_rate: 16000 | ||
speed_perturb: true | ||
fbank_conf: | ||
num_mel_bins: 80 | ||
frame_shift: 10 | ||
frame_length: 25 | ||
dither: 1.0 | ||
spec_aug: true | ||
spec_aug_conf: | ||
num_t_mask: 2 | ||
num_f_mask: 2 | ||
max_t: 50 | ||
max_f: 10 | ||
spec_sub: true | ||
spec_sub_conf: | ||
num_t_sub: 3 | ||
max_t: 30 | ||
spec_trim: false | ||
spec_trim_conf: | ||
max_t: 50 | ||
shuffle: true | ||
shuffle_conf: | ||
shuffle_size: 1500 | ||
sort: true | ||
sort_conf: | ||
sort_size: 500 # sort_size should be less than shuffle_size | ||
batch_conf: | ||
batch_type: 'static' # static or dynamic | ||
batch_size: 16 | ||
|
||
grad_clip: 5 | ||
accum_grad: 1 | ||
max_epoch: 360 | ||
log_interval: 100 | ||
|
||
optim: adam | ||
optim_conf: | ||
lr: 0.001 | ||
scheduler: warmuplr # pytorch v1.1.0+ required | ||
scheduler_conf: | ||
warmup_steps: 25000 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters