b233d46552
* add ctcloss training scripts. * update compute_det_ctc * fix typo. * add fsmn model, can use pretrained kws model from modelscope. * Add streaming detection of CTC model. Add CTC model onnx export. Add CTC model's result in README; For now CTC model runtime is not supported yet. * QA run.sh, maxpooling training scripts is compatible. Ready to PR. * Add a streaming kws demo, support fsmn online forward * fix typo. * Align Stream FSMN and Non-Stream FSMN, both in feature extraction and model forward. * fix repeat activation, add a interval restrict. * fix timestamp when subsampling!=1. * fix flake8, update training script and README, give pretrained ckpt. * fix quickcheck and flake8 * Add realtime CTC-KWS demo in README. --------- Co-authored-by: dujing <dujing@xmov.ai>
65 lines
1.2 KiB
YAML
65 lines
1.2 KiB
YAML
dataset_conf:
|
|
filter_conf:
|
|
max_length: 2048
|
|
min_length: 0
|
|
resample_conf:
|
|
resample_rate: 16000
|
|
speed_perturb: false
|
|
feature_extraction_conf:
|
|
feature_type: 'fbank'
|
|
num_mel_bins: 80
|
|
frame_shift: 10
|
|
frame_length: 25
|
|
dither: 1.
|
|
context_expansion: true
|
|
context_expansion_conf:
|
|
left: 2
|
|
right: 2
|
|
frame_skip: 3
|
|
spec_aug: true
|
|
spec_aug_conf:
|
|
num_t_mask: 1
|
|
num_f_mask: 1
|
|
max_t: 20
|
|
max_f: 10
|
|
shuffle: true
|
|
shuffle_conf:
|
|
shuffle_size: 1500
|
|
batch_conf:
|
|
batch_size: 256
|
|
|
|
model:
|
|
input_dim: 400
|
|
preprocessing:
|
|
type: none
|
|
hidden_dim: 128
|
|
backbone:
|
|
type: fsmn
|
|
input_affine_dim: 140
|
|
num_layers: 4
|
|
linear_dim: 250
|
|
proj_dim: 128
|
|
left_order: 10
|
|
right_order: 2
|
|
left_stride: 1
|
|
right_stride: 1
|
|
output_affine_dim: 140
|
|
classifier:
|
|
type: identity
|
|
dropout: 0.1
|
|
activation:
|
|
type: identity
|
|
|
|
|
|
optim: adam
|
|
optim_conf:
|
|
lr: 0.001
|
|
weight_decay: 0.0001
|
|
|
|
training_config:
|
|
grad_clip: 5
|
|
max_epoch: 80
|
|
log_interval: 10
|
|
criterion: ctc
|
|
|