Upload 3 files

README.md

@@ -0,0 +1,170 @@
+---
+tags:
+  - audio
+  - speech-antispoofing
+  - spoof-detection
+  - voice-liveness
+  - safeear
+  - asvspoof2019
+  - pytorch
+license: apache-2.0
+pipeline_tag: audio-classification
+
+---
+
+# SafeEar ASVspoof2019 Audio Anti-Spoofing Model
+
+[中文](README.zh-CN.md) <!-- Assuming your Chinese file will be named README.zh-CN.md -->
+
+This repository contains an audio anti-spoofing (spoof detection) model pre-trained on the ASVspoof2019 dataset using the SafeEar framework. The model is designed to distinguish between genuine human speech and various types of spoofed audio.
+
+## Model Details
+
+*   **Developers:** HyperStar Team (Zhijiang College of Zhejiang University of Technology)
+*   **Model Type:** Audio Anti-spoofing / Spoof Detection
+*   **Framework:** SafeEar
+*   **Base Models/Tokenizers Used:**
+    *   SpeechTokenizer
+    *   HuBERT Base (ls960)
+*   **Training Dataset:** ASVspoof2019 (Logical Access - LA)
+*   **License:** Apache 2.0
+*   **Supported Languages:** Primarily English, but trained on the diverse ASVspoof2019 dataset.
+
+## Repository File Description
+
+*   `SpeechTokenizer.pt`: Pre-trained SpeechTokenizer model weights.
+*   `hubert_base_ls960.pt`: Pre-trained HuBERT base model weights.
+*   `model.ckpt`: Fine-tuned SafeEar anti-spoofing model checkpoint.
+*   `SafeEar-Inference-Test-Script/`: Directory containing example inference scripts and test audio.
+    *   `audio.flac`: FLAC format audio sample for testing.
+    *   `infer_single_flac.py`: Python script for inference on a single FLAC audio file.
+
+## How to Use
+
+To perform inference with this model using the provided scripts:
+
+1.  **Clone the repository:**
+
+    ```bash
+    git lfs install
+    git clone https://huggingface.co/[your-username]/safeear-asvspoof2019-antispoof
+    cd safeear-asvspoof2019-antispoof
+    ```
+
+2.  **Set up the inference environment:**
+    Ensure Python is installed, along with any necessary libraries that `infer_single_flac.py` might depend on. You may need to check the `SafeEar` framework for its specific dependencies.
+
+3.  **Prepare model files for inference:**
+    Copy the model weights into the inference script directory:
+
+    ```bash
+    cp SpeechTokenizer.pt hubert_base_ls960.pt model.ckpt SafeEar-Inference-Test-Script/
+    ```
+
+4.  **Run the inference script:**
+    Navigate to the script directory and run the script:
+
+    ```bash
+    cd SafeEar-Inference-Test-Script/
+    python infer_single_flac.py
+    ```
+
+    The script is expected to output the prediction results:
+
+    ```json
+    {
+      "label": [
+        1
+      ],
+      "probs": [
+        [
+          0.00033402442932128906,
+          0.9996659755706787
+        ]
+      ]
+    }
+    ```
+
+## Training Details
+
+### Framework
+
+The model was trained using the [SafeEar framework](https://github.com/IDRnD/SafeEar). SafeEar is designed for building robust speech anti-spoofing systems.
+
+### Dataset
+
+The model was trained on the ASVspoof2019 dataset, specifically the Logical Access (LA) partition, which includes various synthetic speech and replay attacks.
+
+### Pre-trained Components
+
+*   **SpeechTokenizer:** Used for speech tokenization.
+*   **HuBERT (hubert_base_ls960):** Used as a powerful speech feature extractor. The `hubert_base_ls960.pt` checkpoint was used as the base.
+
+## Performance Evaluation
+
+The model achieves the following performance on the ASVspoof2019 LA evaluation set:
+
+*   **Equal Error Rate (EER):** 5.275%
+
+![Screenshot 2025-05-20 16.18.05](/Users/tec/Desktop/截屏2025-05-20%2016.18.05.png)
+<!-- Note: This image path is a local path and will likely not work in a public README. It should be replaced with a relative path within the repository or a URL. -->
+
+## Biases, Risks, and Limitations
+
+*   **Generalization to Unseen Attacks:** While trained on diverse spoofing attacks from ASVspoof2019, the model's performance may degrade on entirely new or significantly different spoofing techniques not present in the training data.
+*   **Acoustic Environment Variability:** Highly noisy environments or audio characteristics significantly different from the training data might affect performance.
+*   **Dataset Specificity:** The model is optimized for the attack types and audio present in the ASVspoof2019 dataset. It has not been tested on datasets in other languages.
+*   **Threshold Dependency:** Classification (bona fide/spoof) typically depends on a threshold. The optimal threshold may vary based on the specific requirements of the application.
+
+## Intended Use
+
+This model is intended for researchers and developers working on speech anti-spoofing and voice security applications. It can serve as a baseline for further research or be integrated into systems requiring spoof detection capabilities. It should not be used for critical security applications without further rigorous testing and validation in the target environment.
+
+## How to Cite
+
+If you use this model or the SafeEar framework in your research, please consider citing the relevant publications:
+
+*   **ASVspoof2019:**
+
+    ```bibtex
+    @inproceedings{ASVspoof2019,
+      author={Todisco, Massimiliano and Wang, Xin and Evans, Nicholas and Sahidullah, Md and Delgado, Héctor and Nautsch, Andreas and Yamagishi, Junichi and Lee, Kong Aik and Vestman, Ville and Kinnunen, Tomi and others},
+      title={{ASVspoof 2019: Future horizons in spoofed and fake audio detection}},
+      year={2019},
+      booktitle={Proc. Interspeech 2019},
+      pages={1008--1012},
+      doi={10.21437/Interspeech.2019-2248}
+    }
+    ```
+
+*   **SafeEar:**
+
+    ```bibtex
+    @misc{SafeEar,
+      author    = {Ivan Kukanov, Konstantin Okunev, Alexandra Kuznetsova, Anton Vasiliev},
+      title     = {SafeEar: A versatile framework for speech anti-spoofing},
+      year      = {2023},
+      publisher = {GitHub},
+      journal   = {GitHub repository},
+      howpublished = {\url{https://github.com/IDRnD/SafeEar}}
+    }
+    ```
+
+*   **HuBERT:**
+
+    ```bibtex
+    @article{Hsu2021HuBERT,
+      title={{HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units}},
+      author={Wei-Ning Hsu and Benjamin Bolte and Yao-Hung Hubert Tsai and Kushal Lakhotia and Ruslan Salakhutdinov and Abdelrahman Mohamed},
+      journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
+      year={2021},
+      volume={29},
+      pages={3451-3465},
+      doi={10.1109/TASLP.2021.3122891}
+    }
+    ```
+
+## Author Information
+
+*   **Model Creator:** https://huggingface.co/TEC2004
+*   If you have any questions or feedback, please submit an issue in the repository.

README.zh_CN.md

@@ -0,0 +1,158 @@
+---
+tags:
+  - audio
+  - speech-antispoofing
+  - spoof-detection
+  - voice-liveness
+  - safeear
+  - asvspoof2019
+  - pytorch
+license: apache-2.0
+pipeline_tag: audio-classification
+---
+
+# SafeEar ASVspoof2019 音频反欺诈模型
+
+[English](README.md)
+
+本仓库包含一个使用 SafeEar 框架在 ASVspoof2019 数据集上预训练的音频反欺诈（spoof detection）模型。该模型旨在区分真实人声和各种类型的伪造音频。
+
+## 模型详情
+
+* **开发者：**HyperStar 团队 (浙江工业大学之江学院)
+* **模型类型：** 音频反欺诈 / 伪造检测
+* **框架：** SafeEar
+* **使用的基础模型/分词器：**
+    * SpeechTokenizer
+    * HuBERT Base (ls960)
+* **训练数据集：** ASVspoof2019 (Logical Access - LA)
+* **开源协议：** Apache 2.0
+* **支持语言：** 主要为英语，但在多样化的 ASVspoof2019 数据集上训练。
+
+## 仓库文件说明
+
+* `SpeechTokenizer.pt`: 预训练的 SpeechTokenizer 模型权重。
+* `hubert_base_ls960.pt`: 预训练的 HuBERT 基础模型权重。
+* `model.ckpt`: 微调后的 SafeEar 反欺诈模型检查点。
+* `SafeEar-Inference-Test-Script/`: 包含示例推理脚本和测试音频的目录。
+    * `audio.flac`: 用于测试的 FLAC 格式音频样本。
+    * `infer_single_flac.py`: 对单个 FLAC 音频文件进行推理的 Python 脚本。
+
+## 如何使用
+
+要使用提供的脚本通过此模型进行推理：
+
+1.  **克隆仓库：**
+    ```bash
+    git lfs install
+    git clone [https://huggingface.co/](https://huggingface.co/)[your-username]/safeear-asvspoof2019-antispoof
+    cd safeear-asvspoof2019-antispoof
+    ```
+    
+2.  **设置推理环境：**
+    确保已安装 Python 以及 `infer_single_flac.py` 可能依赖的必要库。您可能需要查看 `SafeEar` 以了解其具体依赖项。
+
+3.  **准备用于推理的模型文件：**
+    将模型权重复制到推理脚本目录中：
+    ```bash
+    cp SpeechTokenizer.pt hubert_base_ls960.pt model.ckpt SafeEar-Inference-Test-Script/
+    ```
+
+4.  **运行推理脚本：**
+    进入脚本目录并运行脚本：
+    
+    ```bash
+    cd SafeEar-Inference-Test-Script/
+    python infer_single_flac.py
+    ```
+    脚本预计会输出预测结果：
+    ```json
+    {
+      "label": [
+        1
+      ],
+      "probs": [
+        [
+          0.00033402442932128906,
+          0.9996659755706787
+        ]
+      ]
+    }
+    ```
+
+## 训练详情
+
+### 框架
+​	该模型使用 [SafeEar 框架](https://github.com/IDRnD/SafeEar)进行训练。SafeEar 旨在构建强大的语音反欺诈系统。
+
+### 数据集
+​	该模型在 ASVspoof2019 数据集上进行了训练，特别是 Logical Access (LA) 部分，其中包括各种合成语音和重放攻击。
+
+### 预训练组件
+* **SpeechTokenizer:** 用于语音分词。
+* **HuBERT (hubert_base_ls960):** 用作强大的语音特征提取器。使用了 `hubert_base_ls960.pt` 检查点作为基础。
+
+## 效果评估
+
+该模型在 ASVspoof2019 LA 评估集上达到以下性能：
+* **等错误率 (EER):** 5.275%
+
+![截屏2025-05-20 16.18.05](/Users/tec/Desktop/截屏2025-05-20 16.18.05.png)
+
+## 偏差、风险与局限性
+
+* **对未知攻击的泛化能力：** 尽管模型在 ASVspoof2019 中的多种欺诈攻击上进行了训练，但对于训练数据中未出现的全新或显著不同的欺诈技术，其性能可能会下降。
+* **声学环境变异性：** 高度嘈杂的环境或与训练数据显著不同的音频特性可能会影响性能。
+* **数据集特异性：** 该模型针对 ASVspoof2019 数据集中的攻击类型和音频进行了优化。在其他语种数据集中为做测试
+* **阈值依赖性：** 分类（真实/欺诈）通常取决于一个阈值。最佳阈值可能会根据应用的具体需求而有所不同。
+
+## 预期用途
+
+​	此模型适用于从事语音反欺诈和语音安全应用的研究人员和开发人员。它可以用作进一步研究的基线，或集成到需要欺诈检测功能的系统中。在目标环境中进行进一步严格测试和验证之前，不应将其用于关键安全应用。
+
+## 如何引用
+
+如果您在研究中使用了此模型或 SafeEar 框架，请考虑引用相关出版物：
+
+* **ASVspoof2019:**
+    ```bibtex
+    @inproceedings{ASVspoof2019,
+      author={Todisco, Massimiliano and Wang, Xin and Evans, Nicholas and Sahidullah, Md and Delgado, Héctor and Nautsch, Andreas and Yamagishi, Junichi and Lee, Kong Aik and Vestman, Ville and Kinnunen, Tomi and others},
+      title={{ASVspoof 2019: Future horizons in spoofed and fake audio detection}},
+      year={2019},
+      booktitle={Proc. Interspeech 2019},
+      pages={1008--1012},
+      doi={10.21437/Interspeech.2019-2248}
+    }
+    ```
+    
+* **SafeEar:**
+    
+    ```bibtex
+    @misc{SafeEar,
+      author    = {Ivan Kukanov, Konstantin Okunev, Alexandra Kuznetsova, Anton Vasiliev},
+      title     = {SafeEar: A versatile framework for speech anti-spoofing},
+      year      = {2023},
+      publisher = {GitHub},
+      journal   = {GitHub repository},
+      howpublished = {\url{[https://github.com/IDRnD/SafeEar](https://github.com/IDRnD/SafeEar)}}
+    }
+    ```
+    
+* **HuBERT:**
+    ```bibtex
+    @article{Hsu2021HuBERT,
+      title={{HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units}},
+      author={Wei-Ning Hsu and Benjamin Bolte and Yao-Hung Hubert Tsai and Kushal Lakhotia and Ruslan Salakhutdinov and Abdelrahman Mohamed},
+      journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
+      year={2021},
+      volume={29},
+      pages={3451-3465},
+      doi={10.1109/TASLP.2021.3122891}
+    }
+    ```
+
+## 作者信息
+
+* **模型创建者：**https://huggingface.co/TEC2004
+* 如果您有任何问题或反馈，请在仓库中提交 issue。

model.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e907978cad9a742fa0b410d653cc72855cccd75eac610e67b2da6a41a944993
+size 762270293