---
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- automatic-speech-recognition
- DewiBrynJones/banc-trawsgrifiadau-bangor-clean-with-ccv
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-xlsr-53-ft-btb-ccv-cy
  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-xlsr-53-ft-btb-ccv-cy

This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the DEWIBRYNJONES/BANC-TRAWSGRIFIADAU-BANGOR-CLEAN-WITH-CCV - DEFAULT dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8413
- Wer: 0.9956

## 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: 16
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 600
- training_steps: 6000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| No log        | 0.0672 | 200  | 3.0805          | 1.0    |
| No log        | 0.1344 | 400  | 2.9226          | 1.0    |
| 4.4646        | 0.2016 | 600  | 1.3392          | 0.8646 |
| 4.4646        | 0.2688 | 800  | 1.0115          | 0.7168 |
| 1.1042        | 0.3360 | 1000 | 0.9009          | 0.6767 |
| 1.1042        | 0.4032 | 1200 | 0.8226          | 0.5948 |
| 1.1042        | 0.4704 | 1400 | 0.8068          | 0.5977 |
| 0.8421        | 0.5376 | 1600 | 0.7186          | 0.5375 |
| 0.8421        | 0.6048 | 1800 | 0.7201          | 0.5561 |
| 0.7637        | 0.6720 | 2000 | 0.6747          | 0.5087 |
| 0.7637        | 0.7392 | 2200 | 0.6709          | 0.5051 |
| 0.7637        | 0.8065 | 2400 | 0.6484          | 0.4850 |
| 0.7134        | 0.8737 | 2600 | 0.6388          | 0.4915 |
| 0.7134        | 0.9409 | 2800 | 0.6279          | 0.4705 |
| 0.6968        | 1.0081 | 3000 | 0.6452          | 0.4833 |
| 0.6968        | 1.0753 | 3200 | 0.6439          | 0.4897 |
| 0.6968        | 1.1425 | 3400 | 0.6750          | 0.5010 |
| 0.667         | 1.2097 | 3600 | 0.7904          | 0.5592 |
| 0.667         | 1.2769 | 3800 | 0.9480          | 0.5801 |
| 0.9326        | 1.3441 | 4000 | 1.1457          | 0.6582 |
| 0.9326        | 1.4113 | 4200 | 1.1183          | 0.6742 |
| 0.9326        | 1.4785 | 4400 | 1.3061          | 0.7807 |
| 1.2308        | 1.5457 | 4600 | 1.2299          | 0.7672 |
| 1.2308        | 1.6129 | 4800 | 1.1784          | 0.7517 |
| 1.2835        | 1.6801 | 5000 | 1.3398          | 0.7625 |
| 1.2835        | 1.7473 | 5200 | 1.5754          | 0.8956 |
| 1.2835        | 1.8145 | 5400 | 1.7280          | 0.9706 |
| 1.6466        | 1.8817 | 5600 | 1.7603          | 0.9727 |
| 1.6466        | 1.9489 | 5800 | 1.8200          | 0.9944 |
| 1.8511        | 2.0161 | 6000 | 1.8413          | 0.9956 |


### Framework versions

- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1