base_config: | |
- egs/egs_bases/syncnet/base.yaml | |
init_from_ckpt: '' | |
binary_data_dir: data/binary/th1kh | |
task_cls: tasks.os_avatar.audio_lm3d_syncnet.SyncNetTask | |
use_kv_dataset: true | |
num_workers: 8 # 4 | |
syncnet_num_clip_pairs: 8192 | |
max_sentences_per_batch: 1024 | |
max_tokens_per_batch: 20000 | |
sample_min_length: 64 | |
max_updates: 400_0000 | |
syncnet_num_layers_per_block: 3 # 3 | |
syncnet_base_hid_size: 128 | |
syncnet_out_hid_size: 1024 # 1024 | |
syncnet_keypoint_mode: lm468 | |
lr: 0.001 | |
lr_decay_rate: 0.98 | |
lr_decay_interval: 5000 | |
audio_type: hubert # hubert | mfcc | |