Downloads · 30 days
4
10% of all-time downloads
YujiYamaguchi/lfm25-audio-jp-dialect-lora
lfm25-audio-jp-dialect-lora is a machine learning model from YujiYamaguchi. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as mit.
Hack the Liquid WAY 2026 — Track 2 / チーム山口
Downloads · 30 days
4
10% of all-time downloads
All-time downloads
42
Public
Repo size
44.4 MB
Likes
1
Public
Click a slice to open those files.
.safetensors44.4 MB · 100%
From the Hugging Face model README
Hack the Liquid WAY 2026 — Track 2 / チーム山口
LFM2.5-Audio-1.5B-JP を LoRA fine-tune した、 方言音声(関西弁・熊本弁)→ 標準語テキスト変換アダプタです。
| モデル | val_loss | 備考 |
|---|---|---|
| lora_convert_v4 (LoRA, 1000 steps) | 0.934 | このアダプタ |
| full_ft_v1 (Full FT, 800 steps) | 0.908 | 参考値(不採用) |
平均CER: 0.40(testセット 50件)/ 推論 1〜2秒(GPU)
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。
federerjiang/dialect.osaka +
federerjiang/dialect.kumamoto