---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- wer
model-index:
- name: xls-r-fleurs_nl-run1
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: audiofolder
      type: audiofolder
      config: default
      split: validation
      args: default
    metrics:
    - name: Wer
      type: wer
      value: 0.4336403033586132
---

<!-- 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. -->

# xls-r-fleurs_nl-run1

This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the FLEURS (nl) dataset.
It achieves the following results on the evaluation set:
- Wer (Validation): 40.36%
- Wer (Test): 40.73%

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 3
- total_train_batch_size: 12
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer (Train)    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 4.9153        | 1.03  | 250  | 2.9252          | 1.0    |
| 2.6885        | 2.05  | 500  | 1.2362          | 0.8548 |
| 0.7443        | 3.08  | 750  | 0.6072          | 0.5436 |
| 0.3497        | 4.11  | 1000 | 0.5776          | 0.4664 |
| 0.2228        | 5.14  | 1250 | 0.5482          | 0.4361 |
| 0.1626        | 6.16  | 1500 | 0.5538          | 0.4166 |
| 0.1301        | 7.19  | 1750 | 0.5696          | 0.4336 |


### Framework versions

- Transformers 4.28.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3