---
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: seq-xls-r-fleurs_zu-run3-asr_xh-run4
  results: []
datasets:
- lucas-meyer/asr_xh
---

<!-- 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. -->

# seq-xls-r-fleurs_zu-run3-asr_xh-run4

This model is a fine-tuned version of [lucas-meyer/xls-r-fleurs_zu-run3](https://huggingface.co/lucas-meyer/xls-r-fleurs_zu-run3) on the asr_xh dataset.
It achieves the following results:
- Wer (Validation): 54.00%
- Wer (Test): 55.18%

### 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)    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 3.7015        | 1.91  | 400  | 0.5528          | 0.7130 |
| 0.4744        | 3.83  | 800  | 0.3950          | 0.5397 |
| 0.2915        | 5.74  | 1200 | 0.4024          | 0.5549 |
| 0.2068        | 7.66  | 1600 | 0.4202          | 0.4947 |


### Framework versions

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