-
Notifications
You must be signed in to change notification settings - Fork 130
/
base_vox_30h.yaml
118 lines (107 loc) · 2.33 KB
/
base_vox_30h.yaml
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
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
# @package _group_
common:
fp16: true
log_format: json
log_interval: 200
tensorboard_logdir: tblog
seed: 1337
user_dir: ???
checkpoint:
save_interval: 2
keep_interval_updates: 1
no_epoch_checkpoints: true
best_checkpoint_metric: accuracy
maximize_best_checkpoint_metric: true
distributed_training:
ddp_backend: c10d
find_unused_parameters: true
distributed_world_size: 8
distributed_port: 29671
nprocs_per_node: 8
task:
_name: av_hubert_pretraining
is_s2s: true
data: ???
label_dir: ???
tokenizer_bpe_model: ???
normalize: true # must be consistent with pre-training
labels: ["wrd"]
single_target: true
fine_tuning: true
stack_order_audio: 4
tokenizer_bpe_name: sentencepiece
max_sample_size: 500
modalities: ["video"]
image_aug: true
pad_audio: true
random_crop: false
dataset:
num_workers: 6
max_tokens: 1000
validate_after_updates: 0
validate_interval: 2
train_subset: train
valid_subset: valid
criterion:
_name: label_smoothed_cross_entropy
report_accuracy: true
label_smoothing: 0.1
optimization:
max_update: 30000
lr: [0.001]
sentence_avg: true
update_freq: [1]
optimizer:
_name: adam
adam_betas: (0.9,0.98)
adam_eps: 1e-08
lr_scheduler:
_name: tri_stage
warmup_steps: 10000
hold_steps: 0
decay_steps: 20000
final_lr_scale: 0.05
model:
_name: av_hubert_seq2seq
w2v_path: ???
apply_mask: false
mask_selection: static
mask_length: 10
mask_other: 0
mask_prob: 0.75
mask_channel_selection: static
mask_channel_length: 64
mask_channel_other: 0
mask_channel_prob: 0.5
layerdrop: 0.1
dropout: 0.0
activation_dropout: 0.1
attention_dropout: 0.0
feature_grad_mult: 1.0
decoder_layers: 6
decoder_dropout: 0.1
decoder_attention_dropout: 0.0
decoder_activation_dropout: 0.1
freeze_finetune_updates: 24000
share_decoder_input_output_embed: true
decoder_normalize_before: true
hydra:
job:
config:
override_dirname:
kv_sep: '-'
item_sep: '__'
exclude_keys:
- run
- task.data
- task.label_dir
- model.w2v_path
- dataset.train_subset
- dataset.valid_subset
- criterion.wer_kenlm_model
- criterion.wer_lexicon
run:
dir: ???
sweep:
dir: ???
subdir: ${hydra.job.config_name}__${hydra.job.override_dirname}