|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: wav2vec2-large-asr-th-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. --> |
|
|
|
# wav2vec2-large-asr-th-2 |
|
|
|
This model was trained from scratch on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1961 |
|
- Wer: 0.3488 |
|
- Cer: 0.0967 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 24 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 3 |
|
- total_train_batch_size: 72 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 600 |
|
- training_steps: 5000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:| |
|
| 0.5833 | 0.36 | 1000 | 0.2734 | 0.4104 | 0.1166 | |
|
| 0.5996 | 0.71 | 2000 | 0.2426 | 0.3957 | 0.1114 | |
|
| 0.4372 | 1.07 | 3000 | 0.2234 | 0.3716 | 0.1029 | |
|
| 0.4109 | 1.42 | 4000 | 0.2070 | 0.3570 | 0.0976 | |
|
| 0.3881 | 1.78 | 5000 | 0.1961 | 0.3488 | 0.0967 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.3 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
