updated README
Browse files
README.md
CHANGED
@@ -25,8 +25,7 @@ model-index:
|
|
25 |
|
26 |
# afrospeech-wav2vec-all-6
|
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).
|
29 |
-
It achieves the following results on the [validation set](VALID_all_interesred_6_audiodata.csv):
|
30 |
|
31 |
- F1: 0.5787048581502744
|
32 |
- Accuracy: 0.6205357142857143
|
@@ -35,21 +34,18 @@ The confusion matrix below helps to give a better look at the model's performanc
|
|
35 |
|
36 |
![confusion matrix](afrospeech-wav2vec-all-6_confusion_matrix_VALID.png)
|
37 |
|
38 |
-
## Model description
|
39 |
|
40 |
-
|
41 |
-
|
42 |
-
## Intended uses & limitations
|
43 |
|
44 |
-
|
45 |
|
46 |
-
## Training and evaluation data
|
47 |
- Size of training set: 1977
|
48 |
- Size of validation set: 396
|
49 |
|
|
|
|
|
50 |
![digits-bar-plot-for-afrospeech](digits-bar-plot-for-afrospeech-wav2vec-all-6.png)
|
51 |
|
52 |
-
## Training procedure
|
53 |
|
54 |
### Training hyperparameters
|
55 |
|
|
|
25 |
|
26 |
# afrospeech-wav2vec-all-6
|
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_all_interesred_6_audiodata.csv):
|
|
|
29 |
|
30 |
- F1: 0.5787048581502744
|
31 |
- Accuracy: 0.6205357142857143
|
|
|
34 |
|
35 |
![confusion matrix](afrospeech-wav2vec-all-6_confusion_matrix_VALID.png)
|
36 |
|
|
|
37 |
|
38 |
+
## Training and evaluation data
|
|
|
|
|
39 |
|
40 |
+
The model was trained on a mixed audio data from 6 African languages - Igbo (`ibo`), Yoruba (`yor`), Rundi (`run`), Oshiwambo (`kua`), Shona (`sna`) and Oromo (`gax`).
|
41 |
|
|
|
42 |
- Size of training set: 1977
|
43 |
- Size of validation set: 396
|
44 |
|
45 |
+
Below is a distribution of the dataset (training and valdation)
|
46 |
+
|
47 |
![digits-bar-plot-for-afrospeech](digits-bar-plot-for-afrospeech-wav2vec-all-6.png)
|
48 |
|
|
|
49 |
|
50 |
### Training hyperparameters
|
51 |
|