Hugging Face's logo

ameerazam08
/
MultiTalk-Code

Model card Files
xet
Community
MultiTalk-Code
File size: 2,203 Bytes 
6931c7b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
DATA:
  dataset: multi
  data_root: sample_dataset
  wav_path: wav
  vertices_path: npy
  template_file: templates.pkl
  read_audio: True
  train_subjects: Arabic English French German Greek Italian Portuguese Russian Spanish Korean Mandarin Japanese
  val_subjects: Arabic English French German Greek Italian Portuguese Russian Spanish Korean Mandarin Japanese
  test_subjects: Arabic English French German Greek Italian Portuguese Russian Spanish Korean Mandarin Japanese
  log_dir:

LOSS:
  loss: MSE
  motion_weight: 1.0
  reg_weight: 1.0


NETWORK:
  arch: stage2
  in_dim: 15069
  hidden_size: 1024
  num_hidden_layers: 6
  num_attention_heads: 8
  intermediate_size: 1536
  window_size: 1
  quant_factor: 0
  face_quan_num: 16
  neg: 0.2
  autoencoder: stage1_vocaset
  INaffine: False
  style_emb_method: nnemb # onehot or nnemb

VQuantizer:
  n_embed: 256
  zquant_dim: 64

PREDICTOR:
  feature_dim: 1024
  vertice_dim: 15069
  device: cuda
  period: 25
  vqvae_pretrained_path: checkpoints/stage1.pth.tar
  wav2vec2model_path: facebook/wav2vec2-large-xlsr-53
  teacher_forcing: True
  num_layers: 6
  n_head: 4 # not used

TRAIN:
  use_sgd: False
  sync_bn: False  # adopt sync_bn or not
  train_gpu: [0]
  workers: 10  # data loader workers
  batch_size: 1  # batch size for training
  batch_size_val: 1  # batch size for validation during training, memory and speed tradeoff
  base_lr: 0.0001
  StepLR: False
  warmup_steps: 1
  adaptive_lr: False
  factor: 0.3
  patience: 3
  threshold: 0.0001
  poly_lr: False
  epochs: 100
  step_size: 100
  gamma: 0.5
  start_epoch: 0
  power: 0.9
  momentum: 0.9
  weight_decay: 0.002
  manual_seed: 131
  print_freq: 10
  save_freq: 1
  save_path:
#  weight:
  weight:
  resume:
  evaluate: True  # evaluate on validation set, extra gpu memory needed and small batch_size_val is recommend
  eval_freq: 5

Distributed:
  dist_url: tcp://127.0.0.1:6701
  dist_backend: 'nccl'
  multiprocessing_distributed: True
  world_size: 1
  rank: 0

TEST:
  test_workers: 0
  test_gpu: [0]
  test_batch_size: 1
  save: True
  model_path: checkpoints/stage2.pth.tar
  save_folder: demo/output
  gt_save_folder: demo/gt
  measure_lve : False
  visualize_mesh : True