|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: results2 |
|
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. --> |
|
|
|
# results2 |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.1078 |
|
- Wer: 0.9945 |
|
|
|
## 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: 0.005 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 3.1667 | 0.57 | 100 | 4.5022 | 0.9941 | |
|
| 2.8372 | 1.14 | 200 | 3.6561 | 0.9989 | |
|
| 2.8065 | 1.71 | 300 | 3.9712 | 0.9943 | |
|
| 2.7851 | 2.29 | 400 | 3.9929 | 0.9941 | |
|
| 2.7765 | 2.86 | 500 | 4.2525 | 0.9942 | |
|
| 2.7666 | 3.43 | 600 | 4.1306 | 0.9941 | |
|
| 2.7647 | 4.0 | 700 | 4.1459 | 0.9941 | |
|
| 2.7572 | 4.57 | 800 | 4.1862 | 0.9944 | |
|
| 2.7506 | 5.14 | 900 | 4.1974 | 0.9948 | |
|
| 2.7481 | 5.71 | 1000 | 4.3590 | 0.9944 | |
|
| 2.7445 | 6.29 | 1100 | 4.1933 | 0.9942 | |
|
| 2.7475 | 6.86 | 1200 | 4.2083 | 0.9948 | |
|
| 2.7431 | 7.43 | 1300 | 4.1181 | 0.9945 | |
|
| 2.7404 | 8.0 | 1400 | 4.1052 | 0.9944 | |
|
| 2.7387 | 8.57 | 1500 | 4.1345 | 0.9945 | |
|
| 2.7365 | 9.14 | 1600 | 4.0646 | 0.9945 | |
|
| 2.7353 | 9.71 | 1700 | 4.1078 | 0.9945 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.15.2 |
|
|
