Edit model card

afrospeech-wav2vec-sna

This model is a fine-tuned version of facebook/wav2vec2-base on the crowd-speech-africa, which was a crowd-sourced dataset collected using the afro-speech Space.

Training and evaluation data

The model was trained on a mixed audio data from Shona (sna).

  • Size of training set: 24
  • Size of validation set: 6

Below is a distribution of the dataset (training and valdation)

digits-bar-plot-for-afrospeech

Evaluation performance

It achieves the following results on the validation set:

  • F1: 1.0
  • Accuracy: 1.0

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.

confusion matrix

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
0.02387 1 1.0
0.0021066 50 1.0
0.001157 100 1.0
0.0009537 150 1.0

Framework versions

  • Transformers 4.21.3
  • Pytorch 1.12.0
  • Datasets 1.14.0
  • Tokenizers 0.12.1
Downloads last month
8

Space using chrisjay/afrospeech-wav2vec-sna 1

Evaluation results