---
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
model-index:
- name: wav2vec2-xls-r-300m-gui-ufe
  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-xls-r-300m-gui-ufe

This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8716
- Cer: 0.2680

## 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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 100
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Cer    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 13.7862       | 0.4329 | 100  | 2.9644          | 1.0    |
| 5.8619        | 0.8658 | 200  | 2.8912          | 1.0    |
| 5.7919        | 1.2987 | 300  | 2.8396          | 1.0    |
| 5.3806        | 1.7316 | 400  | 2.3262          | 0.8814 |
| 4.1562        | 2.1645 | 500  | 1.5810          | 0.4734 |
| 2.8819        | 2.5974 | 600  | 1.1872          | 0.3462 |
| 2.4924        | 3.0303 | 700  | 0.9820          | 0.2758 |
| 1.9214        | 3.4632 | 800  | 0.9245          | 0.2633 |
| 1.7945        | 3.8961 | 900  | 0.8409          | 0.2328 |
| 1.4897        | 4.3290 | 1000 | 0.7835          | 0.2266 |
| 1.4826        | 4.7619 | 1100 | 0.8241          | 0.2209 |
| 1.6168        | 5.1948 | 1200 | 0.9176          | 0.2481 |
| 1.7638        | 5.6277 | 1300 | 0.9793          | 0.2281 |
| 2.2945        | 6.0606 | 1400 | 1.2278          | 0.3211 |
| 2.0624        | 6.4935 | 1500 | 1.0095          | 0.3651 |
| 1.8696        | 6.9264 | 1600 | 0.9520          | 0.2979 |
| 1.6879        | 7.3593 | 1700 | 0.9081          | 0.2756 |
| 1.6352        | 7.7922 | 1800 | 0.8973          | 0.2609 |
| 1.6567        | 8.2251 | 1900 | 0.8858          | 0.2613 |
| 1.5389        | 8.6580 | 2000 | 0.8772          | 0.2613 |
| 1.5732        | 9.0909 | 2100 | 0.8763          | 0.2623 |
| 1.5433        | 9.5238 | 2200 | 0.8728          | 0.2674 |
| 1.5581        | 9.9567 | 2300 | 0.8716          | 0.2680 |


### Framework versions

- Transformers 5.1.0
- Pytorch 2.9.1+cu128
- Datasets 3.6.0
- Tokenizers 0.22.2