configs/test_config.yaml

# Quick test configuration for voice model RL training
# Use this for testing that everything works before full training

# Model settings - using better model than default
model_name: "microsoft/wavlm-base-plus"
device: "cpu"  # Change to "cuda" if you have GPU
checkpoint: null

# Data settings
data_path: "data/raw"
split_ratios:
  train: 0.7
  val: 0.15
  test: 0.15

# RL algorithm settings
algorithm: "ppo"  # or "reinforce"
learning_rate: 0.0003
gamma: 0.99

# PPO-specific
clip_epsilon: 0.2

# Reward function settings
reward_weights:
  clarity: 0.33
  naturalness: 0.33
  accuracy: 0.34

# Training settings - SMALL for quick test
num_episodes: 3        # Just 3 episodes for testing
batch_size: 4          # Small batch for quick runs
episode_length: 10

# Checkpointing
checkpoint_interval: 2  # Save every 2 episodes
checkpoint_dir: "test_run/checkpoints"
max_checkpoints: 3

# Logging and monitoring
log_interval: 1         # Log every episode
log_dir: "test_run/logs"

# Reproducibility
random_seed: 42