|
--- |
|
license: apache-2.0 |
|
tags: |
|
- afro-digits-speech |
|
datasets: |
|
- crowd-speech-africa |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: afrospeech-wav2vec-all-6 |
|
results: |
|
- task: |
|
name: Audio Classification |
|
type: audio-classification |
|
dataset: |
|
name: Afro Speech |
|
type: chrisjay/crowd-speech-africa |
|
args: no |
|
metrics: |
|
- name: Validation Accuracy |
|
type: accuracy |
|
value: 0.6205 |
|
--- |
|
|
|
|
|
# afrospeech-wav2vec-all-6 |
|
|
|
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). |
|
|
|
## Training and evaluation data |
|
|
|
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`). |
|
|
|
- Size of training set: 1977 |
|
- Size of validation set: 396 |
|
|
|
Below is a distribution of the dataset (training and valdation) |
|
|
|
 |
|
|
|
## Evaluation performance |
|
It achieves the following results on the [validation set](VALID_all_interesred_6_audiodata.csv): |
|
|
|
- F1: 0.5787048581502744 |
|
- Accuracy: 0.6205357142857143 |
|
|
|
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. |
|
|
|
 |
|
|
|
## Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 3e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- num_epochs: 150 |
|
|
|
## Training results |
|
|
|
| Training Loss | Epoch | Validation Accuracy | |
|
|:-------------:|:-----:|:--------:| |
|
| 2.0466 | 1 | 0.1130 | |
|
| 0.0468 | 50 | 0.6116 | |
|
| 0.0292 | 100 | 0.5305 | |
|
| 0.0155 | 150 | 0.5319 | |
|
|
|
|
|
|
|
## Framework versions |
|
|
|
- Transformers 4.21.3 |
|
- Pytorch 1.12.0 |
|
- Datasets 1.14.0 |
|
- Tokenizers 0.12.1 |
