Spaces:
Sleeping
Sleeping
defaults: | |
- data: base | |
- eval_data: base | |
- override hydra/job_logging: custom-simplest | |
- _self_ | |
hydra: | |
run: | |
dir: ./output/${exp_id} | |
output_subdir: ${now:%Y-%m-%d_%H-%M-%S}-hydra | |
enable_email: False | |
model: small_16k | |
exp_id: default | |
debug: False | |
cudnn_benchmark: True | |
compile: True | |
amp: True | |
weights: null | |
checkpoint: null | |
seed: 14159265 | |
num_workers: 10 # per-GPU | |
pin_memory: False # set to True if your system can handle it, i.e., have enough memory | |
# NOTE: This DOSE NOT affect the model during inference in any way | |
# they are just for the dataloader to fill in the missing data in multi-modal loading | |
# to change the sequence length for the model, see networks.py | |
data_dim: | |
text_seq_len: 77 | |
clip_dim: 1024 | |
sync_dim: 768 | |
text_dim: 1024 | |
# ema configuration | |
ema: | |
enable: True | |
sigma_rels: [0.05, 0.1] | |
update_every: 1 | |
checkpoint_every: 5_000 | |
checkpoint_folder: ${hydra:run.dir}/ema_ckpts | |
default_output_sigma: 0.05 | |
# sampling | |
sampling: | |
mean: 0.0 | |
scale: 1.0 | |
min_sigma: 0.0 | |
method: euler | |
num_steps: 25 | |
# classifier-free guidance | |
null_condition_probability: 0.1 | |
cfg_strength: 4.5 | |
# checkpoint paths to external modules | |
vae_16k_ckpt: ./ext_weights/v1-16.pth | |
vae_44k_ckpt: ./ext_weights/v1-44.pth | |
bigvgan_vocoder_ckpt: ./ext_weights/best_netG.pt | |
synchformer_ckpt: ./ext_weights/synchformer_state_dict.pth |