configs/fast_experiment.yaml

# Fast experimentation configuration
# Quickly test different reward functions and hyperparameters

model:
  name: "microsoft/wavlm-base-plus"
  enable_rl: true
  action_dim: 256
  action_representation: "discrete"

training:
  device: "cpu"  # Change to "cuda" if you have GPU
  num_episodes: 20  # Moderate number for quick experiments
  batch_size: 16    # Larger batch = faster training per episode
  episode_length: 10
  checkpoint_interval: 10
  checkpoint_dir: "training_runs/fast/checkpoints"
  max_checkpoints: 5
  log_interval: 1
  random_seed: 42

data:
  raw_data_dir: "data/raw"
  sample_rate: 16000
  train_split: 0.7
  val_split: 0.15
  test_split: 0.15

algorithm:
  name: "ppo"
  learning_rate: 0.0003  # Higher LR for faster learning
  gamma: 0.95            # Lower gamma = focus on immediate rewards
  gae_lambda: 0.95
  clip_epsilon: 0.2
  value_loss_coef: 0.5
  entropy_coef: 0.02     # More exploration
  max_grad_norm: 1.0

reward:
  weights:
    clarity: 0.5       # Strong emphasis on clarity
    naturalness: 0.25
    accuracy: 0.25
  use_asr: true
  asr_model: "facebook/wav2vec2-base-960h"

monitoring:
  log_dir: "training_runs/fast/logs"
  visualization_dir: "training_runs/fast/visualizations"
  save_frequency: 5