chat_anything/sad_talker/config/auido2exp.yaml

DATASET:
  TRAIN_FILE_LIST: /apdcephfs_cq2/share_1290939/wenxuazhang/code/file_list/train.txt
  EVAL_FILE_LIST: /apdcephfs_cq2/share_1290939/wenxuazhang/code/file_list/val.txt
  TRAIN_BATCH_SIZE: 32
  EVAL_BATCH_SIZE: 32
  EXP: True
  EXP_DIM: 64
  FRAME_LEN: 32
  COEFF_LEN: 73
  NUM_CLASSES: 46
  AUDIO_ROOT_PATH: /apdcephfs_cq2/share_1290939/wenxuazhang/voxceleb1/wav
  COEFF_ROOT_PATH: /apdcephfs_cq2/share_1290939/wenxuazhang/voxceleb1/wav2lip_3dmm
  LMDB_PATH: /apdcephfs_cq2/share_1290939/shadowcun/datasets/VoxCeleb/v1/imdb
  DEBUG: True
  NUM_REPEATS: 2
  T: 40
  

MODEL:
  FRAMEWORK: V2
  AUDIOENCODER:
    LEAKY_RELU: True
    NORM: 'IN'
  DISCRIMINATOR:
    LEAKY_RELU: False
    INPUT_CHANNELS: 6
  CVAE:
    AUDIO_EMB_IN_SIZE: 512
    AUDIO_EMB_OUT_SIZE: 128
    SEQ_LEN: 32
    LATENT_SIZE: 256
    ENCODER_LAYER_SIZES: [192, 1024]
    DECODER_LAYER_SIZES: [1024, 192]
    

TRAIN:
  MAX_EPOCH: 300
  GENERATOR:
    LR: 2.0e-5
  DISCRIMINATOR:
    LR: 1.0e-5
  LOSS:
    W_FEAT: 0
    W_COEFF_EXP: 2
    W_LM: 1.0e-2
    W_LM_MOUTH: 0
    W_REG: 0
    W_SYNC: 0
    W_COLOR: 0
    W_EXPRESSION: 0
    W_LIPREADING: 0.01
    W_LIPREADING_VV: 0
    W_EYE_BLINK: 4

TAG:
  NAME:  small_dataset