metadata

license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
  - generated_from_trainer
datasets:
  - zeroth_korean
model-index:
  - name: wav2vec2-large-xls-r-300m-korean-g
    results: []

wav2vec2-large-xls-r-300m-korean-g

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

Loss: 0.9772
Cer: 0.1921

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: 0.0001
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1000
num_epochs: 30
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
4.6433	6.49	500	3.2068	0.8114
0.9293	12.99	1000	0.9364	0.2254
0.2504	19.48	1500	0.9958	0.2097
0.1488	25.97	2000	0.9772	0.1921

Framework versions

Transformers 4.38.2
Pytorch 2.0.1+cu118
Datasets 2.18.0
Tokenizers 0.15.2