This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:

Loss: 0.9096
Wer: 0.6547

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: 0.0003
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 200
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
6.8885	0.67	200	3.1346	1.0
3.0233	1.34	400	2.9296	1.0
2.0382	2.02	600	1.4167	0.9138
1.2087	2.69	800	1.1261	0.8175
0.9624	3.36	1000	1.0181	0.7453
0.7902	4.03	1200	0.9485	0.6942
0.6441	4.71	1400	0.9096	0.6547

Framework versions

Transformers 4.32.1
Pytorch 2.0.1+cu118
Datasets 2.14.4
Tokenizers 0.13.3

jcrkn/wav2vec2-large-xls-r-300m-breton-colab_hyper2

wav2vec2-large-xls-r-300m-breton-colab_hyper2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jcrkn/
wav2vec2-large-xls-r-300m-breton-colab_hyper2