pretrained_path: /path/to/VoxCPM2/
train_manifest: /path/to/train.jsonl
val_manifest: null
sample_rate: 16000        # AudioVAE encoder input rate; must match audio_vae_config.sample_rate
out_sample_rate: 48000    # AudioVAE decoder output rate; used for TensorBoard audio logging
batch_size: 2
grad_accum_steps: 8  # effective batch size = batch_size × grad_accum_steps = 16
num_workers: 8
num_iters: 1000
log_interval: 10
valid_interval: 500
save_interval: 500
learning_rate: 0.00001
weight_decay: 0.01
warmup_steps: 100
max_steps: 1000
max_batch_tokens: 8192
max_grad_norm: 1.0        # gradient clipping max norm; 0 = disabled
save_path: /path/to/checkpoints/finetune_all
tensorboard: /path/to/logs/finetune_all
lambdas:
  loss/diff: 1.0
  loss/stop: 1.0