|
--- |
|
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: inf |
|
- Wer: 0.5238 |
|
|
|
## 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: 32 |
|
- 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 | 0.1544 | 200 | inf | 1.0 | |
|
| No log | 0.3089 | 400 | inf | 0.8661 | |
|
| 3.7305 | 0.4633 | 600 | inf | 0.7040 | |
|
| 3.7305 | 0.6178 | 800 | inf | 0.5506 | |
|
| 0.8464 | 0.7722 | 1000 | inf | 0.5168 | |
|
| 0.8464 | 0.9266 | 1200 | inf | 0.4825 | |
|
| 0.8464 | 1.0811 | 1400 | inf | 0.4601 | |
|
| 0.6629 | 1.2355 | 1600 | inf | 0.4445 | |
|
| 0.6629 | 1.3900 | 1800 | inf | 0.4143 | |
|
| 0.5655 | 1.5444 | 2000 | inf | 0.4170 | |
|
| 0.5655 | 1.6988 | 2200 | inf | 0.4047 | |
|
| 0.5655 | 1.8533 | 2400 | inf | 0.3966 | |
|
| 0.5524 | 2.0077 | 2600 | inf | 0.3779 | |
|
| 0.5524 | 2.1622 | 2800 | inf | 0.3737 | |
|
| 0.4773 | 2.3166 | 3000 | inf | 0.3698 | |
|
| 0.4773 | 2.4710 | 3200 | inf | 0.3724 | |
|
| 0.4773 | 2.6255 | 3400 | inf | 0.3584 | |
|
| 0.4694 | 2.7799 | 3600 | inf | 0.3821 | |
|
| 0.4694 | 2.9344 | 3800 | inf | 0.4730 | |
|
| 0.6537 | 3.0888 | 4000 | inf | 0.4754 | |
|
| 0.6537 | 3.2432 | 4200 | inf | 0.5899 | |
|
| 0.6537 | 3.3977 | 4400 | inf | 0.5958 | |
|
| 0.8238 | 3.5521 | 4600 | inf | 0.6336 | |
|
| 0.8238 | 3.7066 | 4800 | inf | 0.6026 | |
|
| 0.8682 | 3.8610 | 5000 | inf | 0.5671 | |
|
| 0.8682 | 4.0154 | 5200 | inf | 0.5378 | |
|
| 0.8682 | 4.1699 | 5400 | inf | 0.5374 | |
|
| 0.855 | 4.3243 | 5600 | inf | 0.5328 | |
|
| 0.855 | 4.4788 | 5800 | inf | 0.5225 | |
|
| 0.9644 | 4.6332 | 6000 | inf | 0.5238 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
