|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: w2v2-base-pretrained_lr1e-4_at0.8_da0.2 |
|
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. --> |
|
|
|
# w2v2-base-pretrained_lr1e-4_at0.8_da0.2 |
|
|
|
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: 1.3297 |
|
- Wer: 0.2683 |
|
|
|
## 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: 0.0001 |
|
- 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: 100 |
|
- num_epochs: 200 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 23.6917 | 10.0 | 100 | 3.6026 | 1.0 | |
|
| 3.259 | 20.0 | 200 | 3.1696 | 1.0 | |
|
| 3.1152 | 30.0 | 300 | 3.1344 | 1.0 | |
|
| 3.0799 | 40.0 | 400 | 3.0976 | 1.0 | |
|
| 3.0793 | 50.0 | 500 | 3.0977 | 1.0 | |
|
| 3.0692 | 60.0 | 600 | 3.0992 | 1.0 | |
|
| 3.0604 | 70.0 | 700 | 3.1350 | 1.0 | |
|
| 3.0397 | 80.0 | 800 | 3.0537 | 1.0 | |
|
| 2.9847 | 90.0 | 900 | 2.9905 | 1.0 | |
|
| 2.5926 | 100.0 | 1000 | 2.2350 | 1.0077 | |
|
| 0.9017 | 110.0 | 1100 | 1.2152 | 0.6301 | |
|
| 0.2326 | 120.0 | 1200 | 1.2279 | 0.4524 | |
|
| 0.1364 | 130.0 | 1300 | 1.2103 | 0.4238 | |
|
| 0.0935 | 140.0 | 1400 | 1.1953 | 0.3926 | |
|
| 0.0759 | 150.0 | 1500 | 1.3237 | 0.3516 | |
|
| 0.0599 | 160.0 | 1600 | 1.3929 | 0.3050 | |
|
| 0.0438 | 170.0 | 1700 | 1.3132 | 0.2717 | |
|
| 0.0389 | 180.0 | 1800 | 1.3469 | 0.2666 | |
|
| 0.0355 | 190.0 | 1900 | 1.3029 | 0.2691 | |
|
| 0.03 | 200.0 | 2000 | 1.3297 | 0.2683 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
