|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-large-xlsr-53 |
|
tags: |
|
- 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 an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: nan |
|
- Wer: 1.0 |
|
|
|
## 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: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1500 |
|
- training_steps: 15000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:------:|:-----:|:---------------:|:------:| |
|
| 5.7778 | 0.0321 | 500 | 2.8852 | 1.0 | |
|
| 1.4914 | 0.0641 | 1000 | 1.2012 | 0.7806 | |
|
| 0.8803 | 0.0962 | 1500 | 1.1212 | 0.7590 | |
|
| 0.7723 | 0.1283 | 2000 | 0.9681 | 0.6770 | |
|
| 0.6988 | 0.1603 | 2500 | 0.9453 | 0.6599 | |
|
| 0.6392 | 0.1924 | 3000 | 0.8691 | 0.6200 | |
|
| 0.6114 | 0.2244 | 3500 | 0.8661 | 0.6192 | |
|
| 0.5807 | 0.2565 | 4000 | 0.7885 | 0.5794 | |
|
| 0.5534 | 0.2886 | 4500 | 0.7739 | 0.5490 | |
|
| 0.5358 | 0.3206 | 5000 | 0.7416 | 0.5415 | |
|
| 0.5189 | 0.3527 | 5500 | 0.7362 | 0.5303 | |
|
| 0.4991 | 0.3848 | 6000 | 0.7188 | 0.5066 | |
|
| 0.48 | 0.4168 | 6500 | 0.6985 | 0.5178 | |
|
| 0.463 | 0.4489 | 7000 | 0.6682 | 0.4933 | |
|
| 0.4477 | 0.4810 | 7500 | 0.6625 | 0.4867 | |
|
| 0.4431 | 0.5130 | 8000 | 0.6374 | 0.4736 | |
|
| 0.4392 | 0.5451 | 8500 | 0.6392 | 0.4772 | |
|
| 0.4197 | 0.5771 | 9000 | 0.6159 | 0.4547 | |
|
| 0.4147 | 0.6092 | 9500 | 0.5995 | 0.4522 | |
|
| 0.3912 | 0.6413 | 10000 | 0.5848 | 0.4286 | |
|
| 0.3742 | 0.6733 | 10500 | 0.5850 | 0.4259 | |
|
| 0.402 | 0.7054 | 11000 | 0.6352 | 0.4489 | |
|
| 0.5746 | 0.7375 | 11500 | 0.7712 | 0.5171 | |
|
| 0.5783 | 0.7695 | 12000 | nan | 1.0 | |
|
| 0.0 | 0.8016 | 12500 | nan | 1.0 | |
|
| 0.0 | 0.8337 | 13000 | nan | 1.0 | |
|
| 0.0 | 0.8657 | 13500 | nan | 1.0 | |
|
| 0.0 | 0.8978 | 14000 | nan | 1.0 | |
|
| 0.0 | 0.9298 | 14500 | nan | 1.0 | |
|
| 0.0 | 0.9619 | 15000 | nan | 1.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
