doc updt

README.md

@@ -25,8 +25,8 @@ Its weights are then downloaded from this repository.
 from spk_embeddings import EmbeddingsModel, compute_embedding
 import torch
 
-nt_extractor = EmbeddingsModel.from_pretrained("Orange/Speaker-wavLM-id")
-nt_extractor.eval()
+model = EmbeddingsModel.from_pretrained("Orange/Speaker-wavLM-id")
+model.eval()
 ```
 
 The model produces normalized vectors as embeddings.
@@ -42,8 +42,8 @@ finally, we can compute two embeddings from two different files and compare them
 wav1 = "/voxceleb1_2019/test/wav/id10270/x6uYqmx31kE/00001.wav"
 wav2 = "/voxceleb1_2019/test/wav/id10270/8jEAjG6SegY/00008.wav"
 
-e1 = compute_embedding(wav1, nt_extractor)
-e2 = compute_embedding(wav2, nt_extractor)
+e1 = compute_embedding(wav1, model)
+e2 = compute_embedding(wav2, model)
 sim = float(torch.matmul(e1,e2.t()))
 
 print(sim) #
@@ -51,8 +51,8 @@ print(sim) #
 
 # Evaluations
 The model has been evaluated on the standard ASV [VoxCeleb1-clean test set](https://www.robots.ox.ac.uk/~vgg/data/voxceleb/meta/veri_test2.txt).
-It results in an Equal Error Rate (EER, lower value denotes a better identification, random prediction leads to a value of 50%) of **10.681%** 
-(with a decision threshold of **0.467**).
+It results in an Equal Error Rate (EER, lower value denotes a better identification, random prediction leads to a value of 50%) of **0.98%** 
+(with a decision threshold of **0.37**).
 
 Please note that the EER value can vary a little depending on the max_size defined to reduce long audios (max 30 seconds in our case).
 
@@ -65,7 +65,7 @@ This model was used as a baseline in the context of voice characterization (pros
 
 In this paper the model is denoted as W-SPK. The other two models used in this study can also be found on HuggingFace :
 - [W-TBR](https://huggingface.co/Orange/Speaker-wavLM-tbr) for timber related embeddings
-- [W-PRO](https://huggingface.co/Orange/Speaker-wavLM-id) for non-timbral embeddings
+- [W-PRO](https://huggingface.co/Orange/Speaker-wavLM-pro) for non-timbral embeddings
 
 
 ### Citation