|
--- |
|
language: |
|
- ko |
|
license: apache-2.0 |
|
base_model: openai/whisper-base |
|
tags: |
|
- hf-asr-leaderboard |
|
- generated_from_trainer |
|
datasets: |
|
- unanam/fleurstest |
|
model-index: |
|
- name: test |
|
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. --> |
|
|
|
# test |
|
|
|
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the whisper_fleurs_ver1 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5203 |
|
- Cer: 10.9470 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 16 |
|
- 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: 500 |
|
- training_steps: 4000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Cer | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:| |
|
| 0.0347 | 6.29 | 1000 | 0.4469 | 10.9426 | |
|
| 0.0046 | 12.58 | 2000 | 0.4908 | 10.8907 | |
|
| 0.0025 | 18.87 | 3000 | 0.5122 | 10.9946 | |
|
| 0.0019 | 25.16 | 4000 | 0.5203 | 10.9470 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.0.dev0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
