6ad6638ba1
Model: iic/speech_paraformer-tiny-commandword_asr_nat-zh-cn-16k-vocab544-pytorch Source: Original Platform
125 lines
2.5 KiB
YAML
125 lines
2.5 KiB
YAML
# network architecture
|
|
model: Paraformer
|
|
model_conf:
|
|
ctc_weight: 0.3
|
|
lsm_weight: 0.1
|
|
length_normalized_loss: false
|
|
predictor_weight: 1.0
|
|
sampling_ratio: 0.4
|
|
share_embedding: true
|
|
|
|
# encoder
|
|
encoder: ConformerEncoder
|
|
encoder_conf:
|
|
output_size: 256
|
|
attention_heads: 4
|
|
linear_units: 320
|
|
num_blocks: 4
|
|
dropout_rate: 0.1
|
|
positional_dropout_rate: 0.1
|
|
attention_dropout_rate: 0.1
|
|
input_layer: linear
|
|
normalize_before: true
|
|
rel_pos_type: latest
|
|
pos_enc_layer_type: rel_pos
|
|
selfattention_layer_type: rel_selfattn
|
|
activation_type: swish
|
|
macaron_style: true
|
|
use_cnn_module: true
|
|
cnn_module_kernel: 13
|
|
|
|
# decoder
|
|
decoder: ParaformerSANDecoder
|
|
decoder_conf:
|
|
attention_heads: 4
|
|
linear_units: 256
|
|
num_blocks: 2
|
|
dropout_rate: 0.1
|
|
positional_dropout_rate: 0.1
|
|
self_attention_dropout_rate: 0.0
|
|
src_attention_dropout_rate: 0.0
|
|
|
|
predictor: CifPredictorV2
|
|
predictor_conf:
|
|
idim: 256
|
|
threshold: 1.0
|
|
l_order: 1
|
|
r_order: 1
|
|
tail_threshold: 0.45
|
|
tail_mask: false
|
|
|
|
# frontend related
|
|
frontend: WavFrontend
|
|
frontend_conf:
|
|
fs: 16000
|
|
window: hamming
|
|
n_mels: 80
|
|
frame_length: 25
|
|
frame_shift: 10
|
|
lfr_m: 7
|
|
lfr_n: 6
|
|
dither: 0.0
|
|
|
|
specaug: SpecAugLFR
|
|
specaug_conf:
|
|
apply_time_warp: false
|
|
time_warp_window: 5
|
|
time_warp_mode: bicubic
|
|
apply_freq_mask: true
|
|
freq_mask_width_range:
|
|
- 0
|
|
- 30
|
|
lfr_rate: 6
|
|
num_freq_mask: 1
|
|
apply_time_mask: true
|
|
time_mask_width_range:
|
|
- 0
|
|
- 12
|
|
num_time_mask: 1
|
|
|
|
train_conf:
|
|
accum_grad: 1
|
|
grad_clip: 5
|
|
max_epoch: 150
|
|
val_scheduler_criterion:
|
|
- valid
|
|
- acc
|
|
best_model_criterion:
|
|
- - valid
|
|
- acc
|
|
- max
|
|
keep_nbest_models: 10
|
|
log_interval: 50
|
|
|
|
optim: adam
|
|
optim_conf:
|
|
lr: 0.0005
|
|
scheduler: warmuplr
|
|
scheduler_conf:
|
|
warmup_steps: 30000
|
|
|
|
dataset: AudioDataset
|
|
dataset_conf:
|
|
index_ds: IndexDSJsonl
|
|
batch_sampler: DynamicBatchLocalShuffleSampler
|
|
batch_type: example # example or length
|
|
batch_size: 1 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
|
|
max_token_length: 2048 # filter samples if source_token_len+target_token_len > max_token_length,
|
|
buffer_size: 500
|
|
shuffle: True
|
|
num_workers: 0
|
|
|
|
tokenizer: CharTokenizer
|
|
tokenizer_conf:
|
|
unk_symbol: <unk>
|
|
split_with_space: true
|
|
|
|
|
|
input_size: 560
|
|
ctc_conf:
|
|
dropout_rate: 0.0
|
|
ctc_type: builtin
|
|
reduce: true
|
|
ignore_nan_grad: true
|
|
normalize: null
|