Downloads · 30 days
0
nii-yamagishilab/whisper-deepfake-word-detection
whisper-deepfake-word-detection is a machine learning model from nii-yamagishilab. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-4.0.
Downloads · 30 days
0
Access
Public
Updated Sep 16, 2026
Repo size
55.6 GB
Likes
0
Public
Click a slice to open those files.
.ckpt55.5 GB · 100%
From the Hugging Face model README
This is the repository for pretraiend models used for paper Deepfake Word Detection by Next-token Prediction using Fine-tuned Whisper
Deepfake Word Detection by Next-token Prediction using Fine-tuned Whisper
Hoan My Tran, Xin Wang, Wanying Ge, Xuechen Liu, Junichi Yamagishi, Interspeech 2026 (accepted)
@inproceedings{tranDeepfake2026,
title = {Deepfake {Word} {Detection} by {Next}-token {Prediction} using {Fine}-tuned {Whisper}},
url = {https://arxiv.org/abs/2602.22658},
booktitle = {Proc. {Interspeech}},
author = {Tran, Hoan My and Wang, Xin and Ge, Wanying and Liu, Xuechen and Yamagishi, Junichi},
month = oct,
year = {2026},
}
Contents
Each folder contains artifacts/checkpoint/*.ckpt, the checkpoint.
Usage:
python main.py <CONFIG> --checkpoint_folder <PATH_TO_CHECKPOINT>checkpoint folder, in which there is ckpt fileLicense: See LICENSE file
Acknowledgement: This work is partially supported by JST, PRESTO Grant (JPMJPR23P9), Japan. It is partially done on TSUBAME4.0, Institute of Science Tokyo. Hoan My Tran was supported by an NII MOU internship program.
Contact: wangxin nii ac jp