|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: wav2vec2-large-asr-th |
|
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 |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1908.0026 |
|
- Cer: 0.9999 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 200 |
|
- training_steps: 1000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Cer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 11752.32 | 0.56 | 100 | 17728.8105 | 1.0360 | |
|
| 3485.8809 | 1.13 | 200 | 2843.4883 | 0.9999 | |
|
| 1825.8963 | 1.69 | 300 | 1949.6913 | 0.9999 | |
|
| 1540.4011 | 2.26 | 400 | 1908.0026 | 0.9999 | |
|
| 1940.8058 | 2.82 | 500 | 1929.7510 | 0.9999 | |
|
| 2261.2883 | 3.39 | 600 | 1879.6377 | 0.9999 | |
|
| 1710.6505 | 3.95 | 700 | 1878.9219 | 0.9999 | |
|
| 1641.3581 | 4.52 | 800 | 1844.1653 | 0.9999 | |
|
| 1888.4705 | 5.08 | 900 | 1846.2725 | 0.9999 | |
|
| 2143.9672 | 5.65 | 1000 | 1846.6494 | 0.9999 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.13.2 |
|
|
