metadata
license: apache-2.0
base_model: facebook/wav2vec2-xlsr-53-espeak-cv-ft
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: tamasheq-99
results: []
tamasheq-99
This model is a fine-tuned version of facebook/wav2vec2-xlsr-53-espeak-cv-ft on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.8641
- 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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 10.0753 | 2.86 | 10 | 10.1435 | 1.6667 |
| 9.4458 | 5.71 | 20 | 9.0880 | 1.0 |
| 8.6766 | 8.57 | 30 | 7.2508 | 1.0 |
| 6.5268 | 11.43 | 40 | 4.9611 | 1.0 |
| 4.9686 | 14.29 | 50 | 3.6603 | 1.0 |
| 3.7601 | 17.14 | 60 | 3.2519 | 1.0 |
| 3.2887 | 20.0 | 70 | 3.0620 | 1.0 |
| 3.1475 | 22.86 | 80 | 2.9495 | 1.0 |
| 3.0013 | 25.71 | 90 | 2.8641 | 1.0 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3