---
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base-960h
tags:
- generated_from_trainer
datasets:
- fleurs
metrics:
- wer
model-index:
- name: low-german
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: fleurs
      type: fleurs
      config: sw_ke
      split: test
      args: sw_ke
    metrics:
    - name: Wer
      type: wer
      value: 1.189170182841069
---

<!-- 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. -->

# low-german

This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the fleurs dataset.
It achieves the following results on the evaluation set:
- Loss: 20.8272
- Wer: 1.1892

## 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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Wer    |
|:-------------:|:-------:|:----:|:---------------:|:------:|
| 0.0           | 31.2540 | 1000 | 20.8277         | 1.1877 |
| 0.0           | 62.5079 | 2000 | 20.8272         | 1.1892 |


### Framework versions

- Transformers 4.53.0
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.2