|
|
|
@ -39,6 +39,7 @@ model_conf:
|
|
|
|
|
ctc_weight: 0.3
|
|
|
|
|
lsm_weight: 0.1 # label smoothing option
|
|
|
|
|
length_normalized_loss: false
|
|
|
|
|
init_type: 'kaiming_uniform'
|
|
|
|
|
|
|
|
|
|
###########################################
|
|
|
|
|
# Data #
|
|
|
|
@ -61,12 +62,12 @@ feat_dim: 80
|
|
|
|
|
stride_ms: 10.0
|
|
|
|
|
window_ms: 25.0
|
|
|
|
|
sortagrad: 0 # Feed samples from shortest to longest ; -1: enabled for all epochs, 0: disabled, other: enabled for 'other' epochs
|
|
|
|
|
batch_size: 64
|
|
|
|
|
batch_size: 32
|
|
|
|
|
maxlen_in: 512 # if input length > maxlen-in, batchsize is automatically reduced
|
|
|
|
|
maxlen_out: 150 # if output length > maxlen-out, batchsize is automatically reduced
|
|
|
|
|
minibatches: 0 # for debug
|
|
|
|
|
batch_count: auto
|
|
|
|
|
batch_bins: 0
|
|
|
|
|
batch_bins: 0
|
|
|
|
|
batch_frames_in: 0
|
|
|
|
|
batch_frames_out: 0
|
|
|
|
|
batch_frames_inout: 0
|
|
|
|
@ -77,13 +78,13 @@ num_encs: 1
|
|
|
|
|
###########################################
|
|
|
|
|
# Training #
|
|
|
|
|
###########################################
|
|
|
|
|
n_epoch: 240
|
|
|
|
|
accum_grad: 2
|
|
|
|
|
n_epoch: 180
|
|
|
|
|
accum_grad: 1
|
|
|
|
|
global_grad_clip: 5.0
|
|
|
|
|
dist_sampler: True
|
|
|
|
|
optim: adam
|
|
|
|
|
optim_conf:
|
|
|
|
|
lr: 0.002
|
|
|
|
|
lr: 0.001
|
|
|
|
|
weight_decay: 1.0e-6
|
|
|
|
|
scheduler: warmuplr
|
|
|
|
|
scheduler_conf:
|
|
|
|
@ -93,4 +94,3 @@ log_interval: 100
|
|
|
|
|
checkpoint:
|
|
|
|
|
kbest_n: 50
|
|
|
|
|
latest_n: 5
|
|
|
|
|
|
|
|
|
|