|
|
|
@ -3,17 +3,20 @@ data:
|
|
|
|
|
train_manifest: data/manifest.train
|
|
|
|
|
dev_manifest: data/manifest.dev
|
|
|
|
|
test_manifest: data/manifest.test
|
|
|
|
|
vocab_filepath: data/vocab.txt
|
|
|
|
|
unit_type: 'char'
|
|
|
|
|
spm_model_prefix: ''
|
|
|
|
|
augmentation_config: conf/augmentation.json
|
|
|
|
|
batch_size: 32
|
|
|
|
|
min_input_len: 0.5
|
|
|
|
|
max_input_len: 20.0 # second
|
|
|
|
|
min_output_len: 0.0
|
|
|
|
|
max_output_len: 400.0
|
|
|
|
|
min_output_input_ratio: 0.05
|
|
|
|
|
max_output_input_ratio: 10.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
collator:
|
|
|
|
|
vocab_filepath: data/vocab.txt
|
|
|
|
|
unit_type: 'char'
|
|
|
|
|
spm_model_prefix: ''
|
|
|
|
|
augmentation_config: conf/augmentation.json
|
|
|
|
|
batch_size: 32
|
|
|
|
|
raw_wav: True # use raw_wav or kaldi feature
|
|
|
|
|
specgram_type: fbank #linear, mfcc, fbank
|
|
|
|
|
feat_dim: 80
|
|
|
|
@ -30,7 +33,7 @@ data:
|
|
|
|
|
keep_transcription_text: False
|
|
|
|
|
sortagrad: True
|
|
|
|
|
shuffle_method: batch_shuffle
|
|
|
|
|
num_workers: 0
|
|
|
|
|
num_workers: 2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# network architecture
|
|
|
|
@ -78,7 +81,7 @@ model:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training:
|
|
|
|
|
n_epoch: 180
|
|
|
|
|
n_epoch: 240
|
|
|
|
|
accum_grad: 4
|
|
|
|
|
global_grad_clip: 5.0
|
|
|
|
|
optim: adam
|
|
|
|
|