---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: wav2vec2-large-xls-r-300m-korean-s5
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# wav2vec2-large-xls-r-300m-korean-s5

This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0236
- Cer: 0.0041

## 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: 8
- eval_batch_size: 8
- 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: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Cer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 8.6117        | 0.39  | 800  | 3.1381          | 0.9999 |
| 0.6539        | 0.78  | 1600 | 0.3426          | 0.0932 |
| 0.3963        | 1.17  | 2400 | 0.1645          | 0.0428 |
| 0.2286        | 1.56  | 3200 | 0.1001          | 0.0254 |
| 0.1656        | 1.94  | 4000 | 0.0567          | 0.0135 |
| 0.1271        | 2.33  | 4800 | 0.0334          | 0.0065 |
| 0.1039        | 2.72  | 5600 | 0.0236          | 0.0041 |


### Framework versions

- Transformers 4.17.0
- Pytorch 1.10.0+cu113
- Datasets 1.18.3
- Tokenizers 0.13.1