Update README.md

README.md

@@ -43,7 +43,7 @@ Download model:
 from huggingface_hub import hf_hub_download
 
 # automatically checks for cached file, optionally set `cache_dir` location
-model_file = hf_hub_download(repo_id='Jenthe/ECAPA2', filename='model.pt', cache_dir=None)
+model_file = hf_hub_download(repo_id='Jenthe/ECAPA2', filename='ecapa2.pt', cache_dir=None)
 ```
 
 
@@ -55,10 +55,10 @@ Extracting speaker embeddings is easy and only requires a few lines of code:
 import torch
 import torchaudio
 
-ecapa2_model = torch.jit.load(model_file, map_location='cpu')
+ecapa2 = torch.jit.load(model_file, map_location='cpu')
 audio, sr = torchaudio.load('sample.wav') # sample rate of 16 kHz expected
 
-embedding = ecapa2_model(audio)
+embedding = ecapa2(audio)
 ```
 
 For faster, 16-bit half-precision CUDA inference (recommended):
@@ -67,11 +67,11 @@ For faster, 16-bit half-precision CUDA inference (recommended):
 import torch
 import torchaudio
 
-ecapa2_model = torch.jit.load(model_file, map_location='cuda')
-ecapa2_model.half() # optional, but results in faster inference
+ecapa2 = torch.jit.load(model_file, map_location='cuda')
+ecapa2.half() # optional, but results in faster inference
 audio, sr = torchaudio.load('sample.wav') # sample rate of 16 kHz expected
 
-embedding = ecapa2_model(audio)
+embedding = ecapa2(audio)
 ```
 
 There is no need for `ecapa2_model.eval()` or `torch.no_grad()`, this is done automatically.
@@ -82,13 +82,13 @@ For the extraction of other hierachical features, the `label` argument can be us
 
 ```python
 # default, only extract the embedding
-feature = ecapa2_model(audio, label='embedding')
+feature = ecapa2(audio, label='embedding')
 
 # concatenates the gfe_1, pool and embedding features
-feature = ecapa2_model(audio, label='gfe_1|pool|embedding')
+feature = ecapa2(audio, label='gfe_1|pool|embedding')
 
 # returns the same output as previous example, concatenation always follows the order of the network
-feature = ecapa2_model(audio, label='embedding|gfe_1|pool')
+feature = ecapa2(audio, label='embedding|gfe_1|pool')
 ```
 
 The following table describes the available features. All features consists of the mean and variance of the frame-level encodings at the indicated layer, expect for the speaker embedding.