import torch
import json
from pathlib import Path
from peft import LoraConfig, get_peft_model
import safetensors.torch as st
from liquid_audio import LFM2AudioModel, LFM2AudioProcessor, ChatState
from huggingface_hub import snapshot_download

# アダプタのダウンロード
adapter_dir = snapshot_download("YujiYamaguchi/lfm25-audio-jp-dialect-lora")

# モデルロード
MODEL_ID = "LiquidAI/LFM2.5-Audio-1.5B-JP"
processor = LFM2AudioProcessor.from_pretrained(MODEL_ID)
model = LFM2AudioModel.from_pretrained(MODEL_ID, device="cuda", dtype=torch.bfloat16)

# LoRA 適用
cfg = json.loads(Path(adapter_dir, "adapter_config.json").read_text())
lora_cfg = LoraConfig(
    r=cfg["r"], lora_alpha=cfg["lora_alpha"],
    target_modules=cfg["target_modules"],
    lora_dropout=cfg.get("lora_dropout", 0.05),
)
model = get_peft_model(model, lora_cfg)
weights = st.load_file(str(Path(adapter_dir, "adapter_model.safetensors")))
model.load_state_dict(weights, strict=False)
model.eval()

詳細は GitHubリポジトリを参照。

学習データ

出典: federerjiang/dialect.osaka + federerjiang/dialect.kumamoto
加工: Qwen3-32B で方言テキスト → 標準語テキストを自動生成
学習ペア: 方言音声 → 標準語テキスト（大阪弁 + 熊本弁計2,600件）