🚨🚨🚨 ATTENTION! 🚨🚨🚨

Use an updated model: https://huggingface.co/Yehor/w2v-bert-uk-v2.1


Community

Overview

This model has apostrophes and hyphens.

The language model is trained on the texts of the Common Voice dataset, which is used during training.

Metrics:

Dataset CER WER
CV7 (no LM) 0.0432 0.2288
CV7 (with LM) 0.0169 0.0706
CV10 (no LM) 0.0412 0.2206
CV10 (with LM) 0.0118 0.0463
Downloads last month
161,808
Safetensors
Model size
315M params
Tensor type
F32
Β·
Inference API
or

Model tree for Yehor/w2v-xls-r-uk

Finetuned
(522)
this model

Dataset used to train Yehor/w2v-xls-r-uk

Space using Yehor/w2v-xls-r-uk 1

Evaluation results