Update README.md

README.md

@@ -12,14 +12,30 @@ base_model:
 
 # 🔍 **SSL-AntiDeepfake**
 
-The **SSL-AntiDeepfake** models are a series of self-supervised learning (SSL) models fine-tuned on multiple datasets of real and deepfake speech. 
-They are trained to classify speech as either "Real" 🟢 or "Fake" 🔴.
-| Repository | Link |
-|------------|------|
-| SSL-AntiDeepfake | [GitHub Repository](https://github.com/nii-yamagishilab/Ultra-SSL-AntiDeepfake) |
+The **SSL-AntiDeepfake** project provides a series of powerful self-supervised learning (SSL) models crafted to **detect deepfake speech** with state-of-the-art accuracy.
 
 
-# 🚀 **Model: Wav2Vec2-Large-AntiDeepfake**
+# 🤖 Available Models
+
+All models are released on Hugging Face 🤗 with two variants:
+- **Default**: Trained with data augmentation
+- **NDA** (No Data Augmentation): Trained without data augmentation
+
+| Model                                    | Variants       |
+|-----------------------------------------------|--------------------|
+| XLS-R-2B-AntiDeepfake | [Default](https://huggingface.co/nii-yamagishilab/xls-r-2b-anti-deepfake), [NDA](https://huggingface.co/nii-yamagishilab/xls-r-2b-anti-deepfake-nda)
+| XLS-R-1B-AntiDeepfake | [Default](https://huggingface.co/nii-yamagishilab/xls-r-1b-anti-deepfake), [NDA](https://huggingface.co/nii-yamagishilab/xls-r-1b-anti-deepfake-nda)
+| MMS-1B-AntiDeepfake | [Default](https://huggingface.co/nii-yamagishilab/mms-1b-anti-deepfake), [NDA](https://huggingface.co/nii-yamagishilab/mms-1b-anti-deepfake-nda)
+| MMS-300M-AntiDeepfake | [Default](https://huggingface.co/nii-yamagishilab/mms-300m-anti-deepfake), [NDA](https://huggingface.co/nii-yamagishilab/mms-300m-anti-deepfake-nda)
+| Wav2Vec2-Large-AntiDeepfake | [Default](https://huggingface.co/nii-yamagishilab/wav2vec-large-anti-deepfake), [NDA](https://huggingface.co/nii-yamagishilab/wav2vec-large-anti-deepfake-nda)
+| Wav2Vec2-Small-AntiDeepfake | [Default](https://huggingface.co/nii-yamagishilab/wav2vec-small-anti-deepfake), [NDA](https://huggingface.co/nii-yamagishilab/wav2vec-small-anti-deepfake-nda)
+| Hubert-Extra-Large-AntiDeepfake | [Default](https://huggingface.co/nii-yamagishilab/hubert-xlarge-anti-deepfake), [NDA](https://huggingface.co/nii-yamagishilab/hubert-xlarge-anti-deepfake-nda)
+
+# 🛠️ Training Code & Repository
+Explore training scripts, config files, and evaluation utilities in our GitHub repository:🔗 [SSL-AntiDeepfake GitHub Repository](https://github.com/nii-yamagishilab/Ultra-SSL-AntiDeepfake)
+
+
+# 🚀 **Model Spotlight: Wav2Vec2-Large-AntiDeepfake**
 
 # 🌟 **Key Features**
 - **Architecture**: Wav2Vec 2.0 - [`facebook/wav2vec2-large-960h-lv60-self `](https://huggingface.co/facebook/wav2vec2-large-960h-lv60-self/tree/main) 🔗.
@@ -43,11 +59,12 @@ They are trained to classify speech as either "Real" 🟢 or "Fake" 🔴.
 ⚠️ **Important:**  
 To run inference with this model, you need to install a specific version of `fairseq` and make manual code modifications. For detailed instructions, please refer to the installation guide in our [GitHub repository](https://github.com/nii-yamagishilab/Ultra-SSL-AntiDeepfake).
 
-For a quicker inference experience, we recommend trying our other SSL-AntiDeepfake models:  
+✅ **Easier Alternatives:**
+We recommend these models for plug-and-play inference: 
 - [MMS-300M-AntiDeepfake](https://huggingface.co/nii-yamagishilab/mms-300m-anti-deepfake)  
 - [MMS-1B-AntiDeepfake](https://huggingface.co/nii-yamagishilab/mms-1b-anti-deepfake)
 
-📦 Dependencies after manual code modifications:
+📦 Dependencies after installing fairseq:
 ```
 pip install huggingface-hub safetensors soundfile
 (pip install huggingface-hub==0.31.1 safetensors==0.5.3 soundfile==0.13.1)
@@ -62,6 +79,9 @@ import torchaudio
 import fairseq
 from huggingface_hub import PyTorchModelHubMixin
 
+# === Detect all audio files in a specified folder ===
+folder_path = "/path/to/folder/contains/wavs/"
+audio_formats = (".mp3", ".wav", ".flac", ".m4a")
 
 # === Download Fairseq checkpoint if not present ===
 # The downloaded checkpoint is used for building front-end architecture,
@@ -138,13 +158,10 @@ model = DeepfakeDetector.from_pretrained("nii-yamagishilab/wav2vec-large-anti-de
 model.eval()
 
 # === Inference on a folder of audio files ===
-folder_path = "path/to/folder/contains/wavs/"
-supported_formats = (".mp3", ".wav", ".flac", ".m4a")
-
 results = []
 for root, _, files in os.walk(folder_path):
     for file in files:
-        if file.lower().endswith(supported_formats):
+        if file.lower().endswith(audio_formats):
             input_path = os.path.join(root, file)
             with torch.no_grad():
                 wav = load_wav_and_preprocess(input_path)
@@ -161,6 +178,8 @@ for file_name, prob in results:
     print(f"{file_name}: real prob = {prob[1]:.3f}, fake prob = {prob[0]:.3f}")
 ```
 # 📊 **Performance Metrics**
+Results shown below can be reproduced using scripts provided in our [GitHub repository](https://github.com/nii-yamagishilab/Ultra-SSL-AntiDeepfake).
+
 | Test Database        | ROC AUC | Accuracy | Precision | Recall | F1-score | FPR   | FNR   | EER (%) @ Threshold |
 |----------------------|---------|----------|-----------|--------|----------|-------|-------|----------------------|
 | ADD2023              | 0.950   | 0.912    | 0.939     | 0.942  | 0.940    | 0.175 | 0.058 | 13.25 @ 0.8520       |
@@ -171,8 +190,9 @@ for file_name, prob in results:
 | WildSVDD-TEST_A      | 0.739   | 0.663    | 0.616     | 0.895  | 0.729    | 0.577 | 0.105 | 34.85 @ 0.9942       |
 | WildSVDD-TEST_B      | 0.654   | 0.696    | 0.740     | 0.836  | 0.785    | 0.583 | 0.164 | 41.67 @ 0.9842       |
 
-
 # **Training Set**
+Below is a breakdown of the training set used for fine-tuning.
+
 | 📚 Database             | 🌍 Language         | ✅ Genuine (hrs) | ❌ Fake (hrs) |
 |----------------------|------------------|----------------|-------------|
 | AISHELL3             | zh               | 85.62          | 0           |
@@ -204,4 +224,17 @@ for file_name, prob in results:
 | VoxCeleb2            | Multilingual     | 1179.62        | 0           |
 | VoxCeleb2-Vocoded    | Multilingual     | 0              | 4721.46     |
 | WaveFake             | en, ja           | 0              | 198.65      |
-| Train Set            | Over 100 languages| 56370.00       | 18280.00    |
+| Train Set            | Over 100 languages| 56370.00       | 18280.00    |
+
+# **Attribution**
+All SSL-AntiDeepfake models were developed by [Yamagishi Lab](https://yamagishilab.jp/) at the National Institute of Informatics (NII), Japan.
+
+All model weights are the intellectual property of NII and are made available for research and educational purposes under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) license.
+
+# **Acknowledgments**
+This project is based on results obtained from project JPNP22007, commissioned by the New Energy and Industrial Technology Development Organization (NEDO).
+
+It is also partially supported by the following grants from the Japan Science and Technology Agency (JST):
+- AIP Acceleration Research (Grant No. JPMJCR24U3)
+- CREST (Grant No. JPMJCR20D3)
+- PRESTO (Grant No. JPMJPR23P9)