runtime/omnivoice-python/omnivoice-source/examples/config/train_config_finetune.json

{
    "llm_name_or_path": "Qwen/Qwen3-0.6B",
    "audio_vocab_size": 1025,
    "audio_mask_id": 1024,
    "num_audio_codebook": 8,

    "audio_codebook_weights": [8, 8, 6, 6, 4, 4, 2, 2],
    "drop_cond_ratio": 0.1,
    "prompt_ratio_range": [0.0, 0.3],
    "mask_ratio_range": [0.0, 1.0],
    "language_ratio": 0.8,
    "use_pinyin_ratio": 0.0,
    "instruct_ratio": 0.0,
    "only_instruct_ratio": 0.0,

    "resume_from_checkpoint": null,
    "init_from_checkpoint": "k2-fsa/OmniVoice",

    "learning_rate": 1e-5,
    "weight_decay": 0.01,
    "max_grad_norm": 1.0,
    "steps": 5000,
    "seed": 42,
    "warmup_type": "ratio",
    "warmup_ratio": 0.01,
    "warmup_steps": 0,

    "batch_tokens": 8192,
    "gradient_accumulation_steps": 1,
    "num_workers": 2,

    "mixed_precision": "bf16",
    "allow_tf32": true,

    "logging_steps": 50,
    "eval_steps": 500,
    "save_steps": 500,
    "keep_last_n_checkpoints": -1
}