Duplicated from misterkissi/w2v2-lg-xls-r-300m-kasem

ghananlpcommunity
/

w2v2-lg-xls-r-300m-kasem

Automatic Speech Recognition

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

w2v2-lg-xls-r-300m-kasem

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

eval_loss: 1.99408
eval_wer: 0.30174
eval_runtime: 308.9313
eval_samples_per_second: 11.252
eval_steps_per_second: 1.408
epoch: 28.8434
step: 57600

Downloads last month: 45

Safetensors

Model size

0.3B params

Tensor type

F32

·

Model tree for ghananlpcommunity/w2v2-lg-xls-r-300m-kasem

Base model

facebook/wav2vec2-xls-r-300m

Finetuned

(888)

this model