File size: 2,348 Bytes
3a88be1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 |
encoder: SenseVoiceEncoderSmall
encoder_conf:
output_size: 512
attention_heads: 4
linear_units: 2048
num_blocks: 50
tp_blocks: 20
dropout_rate: 0.1
positional_dropout_rate: 0.1
attention_dropout_rate: 0.1
input_layer: pe
pos_enc_class: SinusoidalPositionEncoder
normalize_before: true
kernel_size: 11
sanm_shfit: 0
selfattention_layer_type: sanm
model: SenseVoiceSmall
model_conf:
length_normalized_loss: true
sos: 1
eos: 2
ignore_id: -1
tokenizer: SentencepiecesTokenizer
tokenizer_conf:
bpemodel: /root/.cache/modelscope/hub/iic/SenseVoiceSmall/chn_jpn_yue_eng_ko_spectok.bpe.model
unk_symbol: <unk>
split_with_space: true
frontend: WavFrontend
frontend_conf:
fs: 16000
window: hamming
n_mels: 80
frame_length: 25
frame_shift: 10
lfr_m: 7
lfr_n: 6
cmvn_file: /root/.cache/modelscope/hub/iic/SenseVoiceSmall/am.mvn
dataset: SenseVoiceCTCDataset
dataset_conf:
index_ds: IndexDSJsonl
batch_sampler: BatchSampler
data_split_num: 1
batch_type: token
batch_size: 25000
max_token_length: 2000
min_token_length: 60
max_source_length: 2000
min_source_length: 60
max_target_length: 200
min_target_length: 0
shuffle: true
num_workers: 4
sos: 1
eos: 2
IndexDSJsonl: IndexDSJsonl
retry: 20
sort_size: 1024
train_conf:
accum_grad: 1
grad_clip: 5
max_epoch: 100
keep_nbest_models: 10
avg_nbest_model: 10
log_interval: 1
resume: true
validate_interval: 2000
save_checkpoint_interval: 2000
use_deepspeed: false
deepspeed_config: /root/autodl-tmp/SenseVoice/deepspeed_conf/ds_stage1.json
optim: adamw
optim_conf:
lr: 0.0002
scheduler: warmuplr
scheduler_conf:
warmup_steps: 25000
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
init_param: /root/.cache/modelscope/hub/iic/SenseVoiceSmall/model.pt
config: /root/.cache/modelscope/hub/iic/SenseVoiceSmall/config.yaml
is_training: true
trust_remote_code: true
train_data_set_list: /root/autodl-tmp/train/train.jsonl
valid_data_set_list: /root/autodl-tmp/val/val.jsonl
output_dir: ./outputs
model_path: /root/.cache/modelscope/hub/iic/SenseVoiceSmall
device: cpu
|