Update README.md

README.md

@@ -20,10 +20,10 @@ model-index:
       args: fr
     metrics:
     - type: stoi
-      value: 0.679
-      name: Test STOI, in-domain training
+      value: 0.873
+      name: Test SQUIM-STOI, in-domain training
     - type: n-mos
-      value: 3.21
+      value: 3.80
       name: Test Noresqa-MOS, in-domain training
 ---
 
@@ -34,10 +34,11 @@ model-index:
 # Model Card 
 
 - **Developed by:** [Cnam-LMSSC](https://huggingface.co/Cnam-LMSSC)
-- **Model:** [EBEN(M=?,P=?,Q=?)](https://github.com/jhauret/vibravox/blob/main/vibravox/torch_modules/dnn/eben_generator.py) (see [publication in IEEE TASLP](https://ieeexplore.ieee.org/document/10244161) - [arXiv link](https://arxiv.org/abs/2303.10008))
+- **Model:** [EBEN(M=4,P=2,Q=4)](https://github.com/jhauret/vibravox/blob/main/vibravox/torch_modules/dnn/eben_generator.py) (see [publication in IEEE TASLP](https://ieeexplore.ieee.org/document/10244161) - [arXiv link](https://arxiv.org/abs/2303.10008))
 - **Language:** French
 - **License:** MIT
-- **Training dataset:** `speech_noisy` subset of [Cnam-LMSSC/vibravox](https://huggingface.co/datasets/Cnam-LMSSC/vibravox) (see [VibraVox paper on arXiV](https://arxiv.org/abs/2407.11828))
+- **Training dataset:** mix(`speech_clean`+`speechless_noisy`) of [Cnam-LMSSC/vibravox](https://huggingface.co/datasets/Cnam-LMSSC/vibravox) (see [VibraVox paper on arXiV](https://arxiv.org/abs/2407.11828))
+- **Testing dataset:** `speech_noisy` of [Cnam-LMSSC/vibravox](https://huggingface.co/datasets/Cnam-LMSSC/vibravox)
 - **Samplerate for usage:** 16kHz
 
 ## Overview