config/solver/musicgen/musicgen_base_32khz.yaml

# @package __global__

# This is the training loop solver
# for the base MusicGen model (text-to-music)
# on monophonic audio sampled at 32 kHz
defaults:
  - musicgen/default
  - /model: lm/musicgen_lm
  - override /dset: audio/default
  - _self_

autocast: true
autocast_dtype: float16

# EnCodec large trained on mono-channel music audio sampled at 32khz
# with a total stride of 640 leading to 50 frames/s.
# rvq.n_q=4, rvq.bins=2048, no quantization dropout
# (transformer_lm card and n_q must be compatible)
compression_model_checkpoint: //pretrained/facebook/encodec_32khz

channels: 1
sample_rate: 32000

deadlock:
  use: true  # deadlock detection

dataset:
  batch_size: 192  # 32 GPUs
  sample_on_weight: false  # Uniform sampling all the way
  sample_on_duration: false  # Uniform sampling all the way

generate:
  lm:
    use_sampling: true
    top_k: 250
    top_p: 0.0

optim:
  epochs: 500
  optimizer: dadam
  lr: 1
  ema:
    use: true
    updates: 10
    device: cuda

logging:
  log_tensorboard: true

schedule:
  lr_scheduler: cosine
  cosine:
    warmup: 4000
    lr_min_ratio: 0.0
    cycle_length: 1.0