chrisjay commited on
Commit
36ff962
1 Parent(s): 6c36348

added updates

Browse files
Files changed (1) hide show
  1. README.md +12 -9
README.md CHANGED
@@ -25,15 +25,7 @@ model-index:
25
 
26
  # afrospeech-wav2vec-yor
27
 
28
- This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the [crowd-speech-africa](https://huggingface.co/datasets/chrisjay/crowd-speech-africa), which was a crowd-sourced dataset collected using the [afro-speech Space](https://huggingface.co/spaces/chrisjay/afro-speech). It achieves the following results on the [validation set](VALID_yoruba_yor_audio_data.csv):
29
-
30
- - F1: 0.83
31
- - Accuracy: 0.83
32
-
33
- The confusion matrix below helps to give a better look at the model's performance across the digits. Through it, we can see the precision and recall of the model as well as other important insights.
34
-
35
- ![confusion matrix](afrospeech-wav2vec-yor_confusion_matrix_VALID.png)
36
-
37
 
38
  ## Training and evaluation data
39
 
@@ -46,6 +38,17 @@ Below is a distribution of the dataset (training and valdation)
46
 
47
  ![digits-bar-plot-for-afrospeech](digits-bar-plot-for-afrospeech-wav2vec-yor.png)
48
 
 
 
 
 
 
 
 
 
 
 
 
49
 
50
  ### Training hyperparameters
51
 
 
25
 
26
  # afrospeech-wav2vec-yor
27
 
28
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the [crowd-speech-africa](https://huggingface.co/datasets/chrisjay/crowd-speech-africa), which was a crowd-sourced dataset collected using the [afro-speech Space](https://huggingface.co/spaces/chrisjay/afro-speech).
 
 
 
 
 
 
 
 
29
 
30
  ## Training and evaluation data
31
 
 
38
 
39
  ![digits-bar-plot-for-afrospeech](digits-bar-plot-for-afrospeech-wav2vec-yor.png)
40
 
41
+ ## Evaluation performace
42
+ It achieves the following results on the [validation set](VALID_yoruba_yor_audio_data.csv):
43
+ - F1: 0.83
44
+ - Accuracy: 0.83
45
+
46
+ The confusion matrix below helps to give a better look at the model's performance across the digits. Through it, we can see the precision and recall of the model as well as other important insights.
47
+
48
+ ![confusion matrix](afrospeech-wav2vec-yor_confusion_matrix_VALID.png)
49
+
50
+
51
+
52
 
53
  ### Training hyperparameters
54