Update README.md

README.md

@@ -78,14 +78,17 @@ On first run, the model will automatically download the SSL encoder `facebook/wa
 
 ## Evaluation Results
 
-| Model     | ASVspoof19 LA | ASVspoof21 LA | ASVspoof21 DF | ASVspoof5 | ADD2022  | In-the-Wild |
+| Model     | ASVspoof19 LA | ASVspoof21 LA | ASVspoof21 DF | ASVspoof5 | ADD2022  | In-the-Wild | 
 |-----------|--------|--------|--------|--------|--------|--------|
 | [Res2TCNGuard](https://github.com/mtuciru/Res2TCNGuard)      | 7.487  | 19.130 | 19.883 | 37.620 | 49.538 | 49.246 |
 | [AASIST3](https://huggingface.co/lab260/AASIST3)    | 27.585 | 37.407 | 33.099 | 41.001 | 47.192 | 39.626 |
 | [XSLS](https://github.com/QiShanZhang/SLSforASVspoof-2021-DF)      | 0.231  | 7.714  | 4.220  | 17.688 | 33.951 | 7.453 |
 | [TCM-ADD](https://github.com/ductuantruong/tcm_add)       | **0.152** | 6.655  | 3.444 | 19.505 | 35.252 | 7.767 |
 | [DF Arena 1B](https://huggingface.co/Speech-Arena-2025/DF_Arena_1B_V_1)    | 43.793 | 40.137 | 42.994 | 35.333 | 42.139 | 17.598 |
-| **Spectra-AASIST** | 0.159  | **5.164** | **2.568**  | **14.056** | **15.205** | **1.461** |
+| [Spectra-0](https://huggingface.co/lab260/spectra_0) | 0.181  | 6.475 | 5.410  | 14.426 | **14.716** | 1.026 |
+| **[Spectra-AASIST3](https://huggingface.co/lab260/Spectra-AASIST3)** | 0.723  | **4.506** | **1.998**  | **13.82** | 15.187 | **0.961** |
+| **Spectra-AASIST** | 0.159  | 5.164 | 2.568  | 14.056 | 15.205 | 1.461 |
+
 
 ## Quickstart
 
@@ -158,14 +161,14 @@ print({"score_bonafide": score_bonafide, "score_spoof": score_spoof})
 
 In `model.py`, the `SpectraAASIST` class provides `classify()` with a **default threshold** chosen as an “optimal” value for the original setting:
 
-- **Default threshold**: `-1.0625009` (it thresholds `logit_bonafide = logits[:, 1]`)
+- **Default threshold**: `-1.140625` (it thresholds `logit_bonafide = logits[:, 1]`)
 - **Note**: this threshold **may not be optimal** on a different dataset/domain. It’s recommended to tune the threshold on your dataset using **EER** (Equal Error Rate) or a target FAR/FRR.
 
 Example:
 
 ```python
 with torch.inference_mode():
-    pred = model.classify(audio.to(device), threshold=-1.0625009)  # 1=bonafide, 0=spoof
+    pred = model.classify(audio.to(device), threshold=-1.140625)  # 1=bonafide, 0=spoof
 ```
 
 ### Tuning the threshold via EER (typical workflow)