metadata

license: mit
tags:
  - automatic-speech-recognition
  - common_voice
datasets:
  - common_voice
model-index:
  - name: wav2vec2-xls-r-300m-uk
    results: []

wav2vec2-xls-r-300m-uk

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the Common Voice 7.0 dataset.

It achieves the following results on the evaluation set:

Loss: 0.125600
Wer: 0.152833

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

More information needed

Training results

Step	Training Loss	Validation Loss	Wer
4000	0.363600	0.211314	0.305
10000	0.250800	0.178876	0.223011
18000	0.187000	0.163607	0.194422
27200	0.155100	0.153098	0.168595
39600	0.125600	0.141007	0.152833

Framework versions

Transformers 4.11
Pytorch 1.10.0
Datasets 1.13