|
|
---
|
|
|
library_name: transformers
|
|
|
tags:
|
|
|
- generated_from_trainer
|
|
|
metrics:
|
|
|
- wer
|
|
|
model-index:
|
|
|
- name: wav2vec2-base
|
|
|
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-base
|
|
|
|
|
|
This model was trained from scratch on an unknown dataset.
|
|
|
It achieves the following results on the evaluation set:
|
|
|
- Loss: 0.4500
|
|
|
- Wer: 0.2132
|
|
|
|
|
|
## 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: 3e-05
|
|
|
- train_batch_size: 2
|
|
|
- eval_batch_size: 2
|
|
|
- seed: 42
|
|
|
- gradient_accumulation_steps: 2
|
|
|
- total_train_batch_size: 4
|
|
|
- optimizer: Use adafactor and the args are:
|
|
|
No additional optimizer arguments
|
|
|
- lr_scheduler_type: linear
|
|
|
- lr_scheduler_warmup_steps: 100
|
|
|
- training_steps: 6000
|
|
|
|
|
|
### Training results
|
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
|
|
|:-------------:|:-------:|:----:|:---------------:|:------:|
|
|
|
| 0.1825 | 4.4267 | 500 | 0.2557 | 0.2045 |
|
|
|
| 0.1185 | 8.8533 | 1000 | 0.3017 | 0.2121 |
|
|
|
| 0.0937 | 13.2756 | 1500 | 0.3172 | 0.2039 |
|
|
|
| 0.0777 | 17.7022 | 2000 | 0.3681 | 0.2179 |
|
|
|
| 0.059 | 22.1244 | 2500 | 0.4151 | 0.2232 |
|
|
|
| 0.0673 | 26.5511 | 3000 | 0.4483 | 0.2138 |
|
|
|
| 0.0479 | 30.9778 | 3500 | 0.4478 | 0.2168 |
|
|
|
| 0.0463 | 35.4 | 4000 | 0.4102 | 0.2138 |
|
|
|
| 0.0436 | 39.8267 | 4500 | 0.4533 | 0.2109 |
|
|
|
| 0.0355 | 44.2489 | 5000 | 0.4166 | 0.2150 |
|
|
|
| 0.0242 | 48.6756 | 5500 | 0.4591 | 0.2156 |
|
|
|
| 0.0227 | 53.0978 | 6000 | 0.4500 | 0.2132 |
|
|
|
|
|
|
|
|
|
### Framework versions
|
|
|
|
|
|
- Transformers 4.55.1
|
|
|
- Pytorch 2.8.0+cu129
|
|
|
- Datasets 3.6.0
|
|
|
- Tokenizers 0.21.4
|
|
|
|
