---
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- automatic-speech-recognition
- DewiBrynJones/banc-trawsgrifiadau-bangor-clean
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-xlsr-53-ft-btb-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-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 - DEFAULT dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2310
- Wer: 0.9240

## 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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 6000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| No log        | 0.1139 | 200  | 3.1075          | 1.0    |
| No log        | 0.2278 | 400  | 1.6249          | 0.8958 |
| 3.6043        | 0.3417 | 600  | 1.1246          | 0.8676 |
| 3.6043        | 0.4556 | 800  | 0.9142          | 0.7094 |
| 1.0665        | 0.5695 | 1000 | 0.7570          | 0.5934 |
| 1.0665        | 0.6834 | 1200 | 0.6980          | 0.5285 |
| 1.0665        | 0.7973 | 1400 | 0.6942          | 0.5389 |
| 0.8811        | 0.9112 | 1600 | 0.6152          | 0.4862 |
| 0.8811        | 1.0251 | 1800 | 0.5941          | 0.4535 |
| 0.7654        | 1.1390 | 2000 | 0.5642          | 0.4329 |
| 0.7654        | 1.2528 | 2200 | 0.5727          | 0.4313 |
| 0.7654        | 1.3667 | 2400 | 0.5467          | 0.4317 |
| 0.6896        | 1.4806 | 2600 | 0.5658          | 0.4398 |
| 0.6896        | 1.5945 | 2800 | 0.6008          | 0.4445 |
| 0.7558        | 1.7084 | 3000 | 0.7090          | 0.5021 |
| 0.7558        | 1.8223 | 3200 | 0.8050          | 0.5291 |
| 0.7558        | 1.9362 | 3400 | 0.8248          | 0.5275 |
| 0.9823        | 2.0501 | 3600 | 0.7945          | 0.5073 |
| 0.9823        | 2.1640 | 3800 | 0.7690          | 0.4982 |
| 0.9181        | 2.2779 | 4000 | 0.8669          | 0.6930 |
| 0.9181        | 2.3918 | 4200 | 0.8887          | 0.6311 |
| 0.9181        | 2.5057 | 4400 | 1.1509          | 0.8436 |
| 1.0805        | 2.6196 | 4600 | 1.2167          | 0.9459 |
| 1.0805        | 2.7335 | 4800 | 1.2323          | 0.9307 |
| 1.3977        | 2.8474 | 5000 | 1.6597          | 0.9528 |
| 1.3977        | 2.9613 | 5200 | 2.0224          | 0.9162 |
| 1.3977        | 3.0752 | 5400 | 2.1054          | 0.9104 |
| 2.1028        | 3.1891 | 5600 | 2.2486          | 0.9281 |
| 2.1028        | 3.3030 | 5800 | 2.2447          | 0.9216 |
| 2.2911        | 3.4169 | 6000 | 2.2310          | 0.9240 |


### Framework versions

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