metadata

language:
  - sw
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: wav2vec-xls-r
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: sw
          split: test
          args: 'config: sw, split: train+test'
        metrics:
          - name: Wer
            type: wer
            value: 0.9982181245473462

wav2vec-xls-r

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

Loss: 2.1585
Wer: 0.9982

Increase the number of epochs to improve performance or use a bigger model.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.0131	1.53	1000	3.0846	1.0
2.322	3.07	2000	2.6234	1.0000
1.3523	4.6	3000	2.2515	0.9991
1.1727	6.13	4000	2.1585	0.9982

Framework versions

Transformers 4.34.1
Pytorch 2.0.1+cu118
Datasets 2.14.6
Tokenizers 0.14.1