---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- google/fleurs
metrics:
- wer
model-index:
- name: xls-r-fleurs_zu-run4
  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: 0.6643247462919594
---

<!-- 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_zu-run4

This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the FLEURS (zu) dataset.
It achieves the following results:
- Wer (Validation): 67.79%
- Wer (Test): 67.97%

### 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)   |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 13.7467       | 0.58  | 100  | 4.7915          | 1.0    |
| 3.7307        | 1.17  | 200  | 3.0551          | 1.0    |
| 3.0005        | 1.75  | 300  | 2.9790          | 1.0    |
| 2.5651        | 2.33  | 400  | 1.5112          | 1.0    |
| 0.7838        | 2.91  | 500  | 0.7741          | 0.7796 |
| 0.4975        | 3.5   | 600  | 0.7511          | 0.7585 |
| 0.4131        | 4.08  | 700  | 0.6563          | 0.7023 |
| 0.3097        | 4.66  | 800  | 0.5946          | 0.6779 |
| 0.2777        | 5.24  | 900  | 0.6919          | 0.6950 |
| 0.2548        | 5.83  | 1000 | 0.6429          | 0.6734 |
| 0.2172        | 6.41  | 1100 | 0.6553          | 0.6643 |


### Framework versions

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