fbadine commited on
Commit
fa2f032
1 Parent(s): 09b45e2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -13
README.md CHANGED
@@ -1,17 +1,9 @@
1
  ---
2
  license: apache-2.0
3
  ---
4
- # UK & Ireland Accent Classification Model
5
 
6
- This is a model to classify and identify the accent of a UK or Ireland speaker among one of the following accents:
7
- * Irish English
8
- * Midlands English
9
- * Northern English
10
- * Scottish English
11
- * Southern English
12
- * Welsh English
13
-
14
- The model implements transfer learning feature extraction using [Yamnet](https://tfhub.dev/google/yamnet/1) model in order to train a model.
15
 
16
  ### Yamnet Model
17
  Yamnet is an audio event classifier trained on the AudioSet dataset to predict audio events from the AudioSet ontology. It is available on TensorFlow Hub.
@@ -21,12 +13,14 @@ As output, the model returns a 3-tuple:
21
  - Embeddings of shape `(N, 1024)`.
22
  - The log-mel spectrogram of the entire audio frame.
23
 
24
- We will use the embeddings, which are the features extracted from the audio samples, as the input to our dense model.
 
 
25
 
26
  ### Dense Model
27
  The dense model that we used consists of:
28
  - An input layer which is embedding output of the Yamnet classifier.
29
- - 4 dense hidden layers and 4 dropout layers
30
  - An output dense layer.
31
 
32
  <details>
@@ -36,7 +30,8 @@ The dense model that we used consists of:
36
 
37
  </details>
38
 
39
- ### Results
 
40
  The model achieved the following results:
41
 
42
  Results | Training | Validation
@@ -61,6 +56,9 @@ native speakers of Southern England, Midlands, Northern England, Wales, Scotland
61
  For more info, please refer to the above link or to the following paper:
62
  [Open-source Multi-speaker Corpora of the English Accents in the British Isles](https://aclanthology.org/2020.lrec-1.804.pdf)
63
 
 
 
 
64
  ---
65
  ## Demo
66
  A demo is available in HuggingFace Spaces ...
 
1
  ---
2
  license: apache-2.0
3
  ---
4
+ ## UK & Ireland Accent Classification Model
5
 
6
+ This model classifies UK & Ireland accents using feature extraction from [Yamnet](https://tfhub.dev/google/yamnet/1).
 
 
 
 
 
 
 
 
7
 
8
  ### Yamnet Model
9
  Yamnet is an audio event classifier trained on the AudioSet dataset to predict audio events from the AudioSet ontology. It is available on TensorFlow Hub.
 
13
  - Embeddings of shape `(N, 1024)`.
14
  - The log-mel spectrogram of the entire audio frame.
15
 
16
+ We will use the embeddings, which are the features extracted from the audio samples, as the input to our dense model.
17
+
18
+ For more detailed information about Yamnet, please refer to its [TensorFlow Hub](https://tfhub.dev/google/yamnet/1) page.
19
 
20
  ### Dense Model
21
  The dense model that we used consists of:
22
  - An input layer which is embedding output of the Yamnet classifier.
23
+ - 4 dense hidden layers and 4 dropout layers.
24
  - An output dense layer.
25
 
26
  <details>
 
30
 
31
  </details>
32
 
33
+ ---
34
+ ## Results
35
  The model achieved the following results:
36
 
37
  Results | Training | Validation
 
56
  For more info, please refer to the above link or to the following paper:
57
  [Open-source Multi-speaker Corpora of the English Accents in the British Isles](https://aclanthology.org/2020.lrec-1.804.pdf)
58
 
59
+ ---
60
+ ## How to use
61
+
62
  ---
63
  ## Demo
64
  A demo is available in HuggingFace Spaces ...