|
|
--- |
|
|
language: |
|
|
- en |
|
|
license: apache-2.0 |
|
|
base_model: openai/whisper-medium |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- wer |
|
|
model-index: |
|
|
- name: openai/whisper-medium |
|
|
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. --> |
|
|
|
|
|
# openai/whisper-medium |
|
|
|
|
|
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the pphuc25/EngMed dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.3644 |
|
|
- Wer: 27.0471 |
|
|
|
|
|
## 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: 8 |
|
|
- 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: 100 |
|
|
- num_epochs: 20 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:| |
|
|
| 0.9369 | 1.0 | 3491 | 1.0416 | 45.5524 | |
|
|
| 0.6193 | 2.0 | 6982 | 0.9804 | 37.6418 | |
|
|
| 0.3774 | 3.0 | 10473 | 0.9933 | 42.7926 | |
|
|
| 0.268 | 4.0 | 13964 | 1.0419 | 34.9683 | |
|
|
| 0.2095 | 5.0 | 17455 | 1.1003 | 32.7617 | |
|
|
| 0.1284 | 6.0 | 20946 | 1.1458 | 31.5065 | |
|
|
| 0.0925 | 7.0 | 24437 | 1.1670 | 31.7984 | |
|
|
| 0.0932 | 8.0 | 27928 | 1.2259 | 30.5314 | |
|
|
| 0.0612 | 9.0 | 31419 | 1.2532 | 32.1152 | |
|
|
| 0.0489 | 10.0 | 34910 | 1.2556 | 30.6472 | |
|
|
| 0.0313 | 11.0 | 38401 | 1.3001 | 30.0870 | |
|
|
| 0.0241 | 12.0 | 41892 | 1.2982 | 30.4427 | |
|
|
| 0.0237 | 13.0 | 45383 | 1.3242 | 29.9322 | |
|
|
| 0.0186 | 14.0 | 48874 | 1.3390 | 28.2798 | |
|
|
| 0.0063 | 15.0 | 52365 | 1.3588 | 29.5764 | |
|
|
| 0.0041 | 16.0 | 55856 | 1.3580 | 28.5777 | |
|
|
| 0.0014 | 17.0 | 59347 | 1.3533 | 27.6901 | |
|
|
| 0.0014 | 18.0 | 62838 | 1.3609 | 28.0742 | |
|
|
| 0.0001 | 19.0 | 66329 | 1.3597 | 28.3330 | |
|
|
| 0.0002 | 20.0 | 69820 | 1.3644 | 27.0471 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.41.1 |
|
|
- Pytorch 2.3.0 |
|
|
- Datasets 2.19.1 |
|
|
- Tokenizers 0.19.1 |
|
|
|
