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
| model: funasr.cli.models.paraformer:Paraformer
| model_conf:
| ctc_weight: 0.3
| lsm_weight: 0.1
| length_normalized_loss: false
| predictor_weight: 1.0
| sampling_ratio: 0.4
| use_1st_decoder_loss: true
| frontend: wav_frontend
| frontend_conf:
| fs: 16000
| window: hamming
| n_mels: 80
| frame_length: 25
| frame_shift: 10
| lfr_m: 1
| lfr_n: 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
| specaug: specaug
| specaug_conf:
| apply_time_warp: true
| time_warp_window: 5
| time_warp_mode: bicubic
| apply_freq_mask: true
| freq_mask_width_range:
| - 0
| - 30
| num_freq_mask: 2
| apply_time_mask: true
| time_mask_width_range:
| - 0
| - 40
| num_time_mask: 2
| predictor: cif_predictor
| predictor_conf:
| idim: 256
| threshold: 1.0
| l_order: 1
| r_order: 1
| tail_threshold: 0.45
| dataset_conf:
| data_names: speech,text
| data_types: sound,text
| shuffle: true
| shuffle_conf:
| shuffle_size: 2048
| sort_size: 500
| batch_conf:
| batch_type: example
| batch_size: 2
| num_workers: 8
| normalize: null
| model_pretrain: damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch
| token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt
| train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl
| output_dir: /nfs/zhifu.gzf/ckpt/funasr2/exp2
|
|
