|
--- |
|
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: 0.4404 |
|
- Wer: 0.3235 |
|
|
|
## 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: 64 |
|
- 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: 5000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:------:|:----:|:---------------:|:------:| |
|
| No log | 0.0566 | 100 | 3.5966 | 1.0 | |
|
| No log | 0.1133 | 200 | 3.5808 | 1.0 | |
|
| No log | 0.1699 | 300 | 2.2642 | 0.9884 | |
|
| No log | 0.2265 | 400 | 1.0231 | 0.7426 | |
|
| 3.6826 | 0.2831 | 500 | 0.9161 | 0.6457 | |
|
| 3.6826 | 0.3398 | 600 | 0.7942 | 0.5827 | |
|
| 3.6826 | 0.3964 | 700 | 0.7551 | 0.5417 | |
|
| 3.6826 | 0.4530 | 800 | 0.7243 | 0.5352 | |
|
| 3.6826 | 0.5096 | 900 | 0.6665 | 0.4985 | |
|
| 0.4714 | 0.5663 | 1000 | 0.6403 | 0.4863 | |
|
| 0.4714 | 0.6229 | 1100 | 0.6220 | 0.4727 | |
|
| 0.4714 | 0.6795 | 1200 | 0.6100 | 0.4642 | |
|
| 0.4714 | 0.7361 | 1300 | 0.5863 | 0.4442 | |
|
| 0.4714 | 0.7928 | 1400 | 0.5668 | 0.4384 | |
|
| 0.3661 | 0.8494 | 1500 | 0.5753 | 0.4421 | |
|
| 0.3661 | 0.9060 | 1600 | 0.5641 | 0.4311 | |
|
| 0.3661 | 0.9626 | 1700 | 0.5466 | 0.4153 | |
|
| 0.3661 | 1.0193 | 1800 | 0.5304 | 0.4023 | |
|
| 0.3661 | 1.0759 | 1900 | 0.5280 | 0.3938 | |
|
| 0.3069 | 1.1325 | 2000 | 0.5220 | 0.3902 | |
|
| 0.3069 | 1.1891 | 2100 | 0.5064 | 0.3929 | |
|
| 0.3069 | 1.2458 | 2200 | 0.5033 | 0.3823 | |
|
| 0.3069 | 1.3024 | 2300 | 0.4920 | 0.3773 | |
|
| 0.3069 | 1.3590 | 2400 | 0.4955 | 0.3737 | |
|
| 0.264 | 1.4156 | 2500 | 0.4955 | 0.3739 | |
|
| 0.264 | 1.4723 | 2600 | 0.4846 | 0.3651 | |
|
| 0.264 | 1.5289 | 2700 | 0.4761 | 0.3645 | |
|
| 0.264 | 1.5855 | 2800 | 0.4672 | 0.3627 | |
|
| 0.264 | 1.6421 | 2900 | 0.4645 | 0.3640 | |
|
| 0.2498 | 1.6988 | 3000 | 0.4652 | 0.3589 | |
|
| 0.2498 | 1.7554 | 3100 | 0.4596 | 0.3534 | |
|
| 0.2498 | 1.8120 | 3200 | 0.4505 | 0.3510 | |
|
| 0.2498 | 1.8686 | 3300 | 0.4490 | 0.3522 | |
|
| 0.2498 | 1.9253 | 3400 | 0.4460 | 0.3456 | |
|
| 0.2304 | 1.9819 | 3500 | 0.4440 | 0.3405 | |
|
| 0.2304 | 2.0385 | 3600 | 0.4493 | 0.3425 | |
|
| 0.2304 | 2.0951 | 3700 | 0.4386 | 0.3374 | |
|
| 0.2304 | 2.1518 | 3800 | 0.4424 | 0.3381 | |
|
| 0.2304 | 2.2084 | 3900 | 0.4385 | 0.3373 | |
|
| 0.1947 | 2.2650 | 4000 | 0.4394 | 0.3355 | |
|
| 0.1947 | 2.3216 | 4100 | 0.4354 | 0.3324 | |
|
| 0.1947 | 2.3783 | 4200 | 0.4345 | 0.3325 | |
|
| 0.1947 | 2.4349 | 4300 | 0.4343 | 0.3331 | |
|
| 0.1947 | 2.4915 | 4400 | 0.4517 | 0.3349 | |
|
| 0.1996 | 2.5481 | 4500 | 0.4571 | 0.3328 | |
|
| 0.1996 | 2.6048 | 4600 | 0.4423 | 0.3255 | |
|
| 0.1996 | 2.6614 | 4700 | 0.4405 | 0.3254 | |
|
| 0.1996 | 2.7180 | 4800 | 0.4437 | 0.3238 | |
|
| 0.1996 | 2.7746 | 4900 | 0.4401 | 0.3232 | |
|
| 0.2024 | 2.8313 | 5000 | 0.4404 | 0.3235 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
