|
|
|
@ -4,11 +4,11 @@ data:
|
|
|
|
|
dev_manifest: data/manifest.dev
|
|
|
|
|
test_manifest: data/manifest.test-clean
|
|
|
|
|
min_input_len: 0.5 # seconds
|
|
|
|
|
max_input_len: 20.0 # seconds
|
|
|
|
|
max_input_len: 30.0 # seconds
|
|
|
|
|
min_output_len: 0.0 # tokens
|
|
|
|
|
max_output_len: 400.0 # tokens
|
|
|
|
|
min_output_input_ratio: 0.05
|
|
|
|
|
max_output_input_ratio: 10.0
|
|
|
|
|
max_output_input_ratio: 100.0
|
|
|
|
|
|
|
|
|
|
collator:
|
|
|
|
|
vocab_filepath: data/vocab.txt
|
|
|
|
@ -16,7 +16,7 @@ collator:
|
|
|
|
|
spm_model_prefix: 'data/bpe_unigram_5000'
|
|
|
|
|
mean_std_filepath: ""
|
|
|
|
|
augmentation_config: conf/augmentation.json
|
|
|
|
|
batch_size: 32
|
|
|
|
|
batch_size: 16
|
|
|
|
|
raw_wav: True # use raw_wav or kaldi feature
|
|
|
|
|
spectrum_type: fbank #linear, mfcc, fbank
|
|
|
|
|
feat_dim: 80
|
|
|
|
@ -80,7 +80,7 @@ model:
|
|
|
|
|
|
|
|
|
|
training:
|
|
|
|
|
n_epoch: 120
|
|
|
|
|
accum_grad: 4
|
|
|
|
|
accum_grad: 8
|
|
|
|
|
global_grad_clip: 3.0
|
|
|
|
|
optim: adam
|
|
|
|
|
optim_conf:
|
|
|
|
|