|
--- |
|
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_da0.1 |
|
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_da0.1 |
|
|
|
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: 17.4872 |
|
- 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: 0.0001 |
|
- 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: 1000 |
|
- training_steps: 3500 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:---:| |
|
| 37.4028 | 50.0 | 250 | 20.8788 | 1.0 | |
|
| 15.6492 | 100.0 | 500 | 19.7127 | 1.0 | |
|
| 16.1334 | 150.0 | 750 | 20.9635 | 1.0 | |
|
| 20.9127 | 200.0 | 1000 | 17.5870 | 1.0 | |
|
| 18.6712 | 250.0 | 1250 | 17.4758 | 1.0 | |
|
| 18.5148 | 300.0 | 1500 | 17.4736 | 1.0 | |
|
| 18.4769 | 350.0 | 1750 | 17.4742 | 1.0 | |
|
| 18.5946 | 400.0 | 2000 | 17.5825 | 1.0 | |
|
| 18.4632 | 450.0 | 2250 | 17.4559 | 1.0 | |
|
| 18.3947 | 500.0 | 2500 | 17.4270 | 1.0 | |
|
| 18.573 | 550.0 | 2750 | 17.5461 | 1.0 | |
|
| 18.4756 | 600.0 | 3000 | 17.5971 | 1.0 | |
|
| 18.4707 | 650.0 | 3250 | 17.5327 | 1.0 | |
|
| 18.5019 | 700.0 | 3500 | 17.4872 | 1.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|