|
|
--- |
|
|
language: |
|
|
- en |
|
|
license: apache-2.0 |
|
|
base_model: openai/whisper-tiny |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- wer |
|
|
model-index: |
|
|
- name: openai/whisper-tiny |
|
|
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-tiny |
|
|
|
|
|
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the pphuc25/EngMed dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.4835 |
|
|
- Wer: 32.2972 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:| |
|
|
| 0.8402 | 1.0 | 3491 | 0.9453 | 45.4910 | |
|
|
| 0.5871 | 2.0 | 6982 | 0.9525 | 54.3790 | |
|
|
| 0.3779 | 3.0 | 10473 | 0.9838 | 38.5673 | |
|
|
| 0.2907 | 4.0 | 13964 | 1.0268 | 38.9408 | |
|
|
| 0.2155 | 5.0 | 17455 | 1.1086 | 47.6326 | |
|
|
| 0.1331 | 6.0 | 20946 | 1.1735 | 37.2778 | |
|
|
| 0.1051 | 7.0 | 24437 | 1.2287 | 43.8694 | |
|
|
| 0.0862 | 8.0 | 27928 | 1.2749 | 38.3380 | |
|
|
| 0.051 | 9.0 | 31419 | 1.3181 | 38.1879 | |
|
|
| 0.0505 | 10.0 | 34910 | 1.3519 | 37.6607 | |
|
|
| 0.0235 | 11.0 | 38401 | 1.3838 | 34.7355 | |
|
|
| 0.0172 | 12.0 | 41892 | 1.4131 | 34.8962 | |
|
|
| 0.0145 | 13.0 | 45383 | 1.4257 | 34.5925 | |
|
|
| 0.0102 | 14.0 | 48874 | 1.4460 | 34.5535 | |
|
|
| 0.0063 | 15.0 | 52365 | 1.4482 | 33.0453 | |
|
|
| 0.0023 | 16.0 | 55856 | 1.4666 | 32.8515 | |
|
|
| 0.0017 | 17.0 | 59347 | 1.4708 | 32.4284 | |
|
|
| 0.004 | 18.0 | 62838 | 1.4847 | 32.8149 | |
|
|
| 0.0002 | 19.0 | 66329 | 1.4768 | 32.1459 | |
|
|
| 0.0001 | 20.0 | 69820 | 1.4835 | 32.2972 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.41.1 |
|
|
- Pytorch 2.3.0 |
|
|
- Datasets 2.19.1 |
|
|
- Tokenizers 0.19.1 |
|
|
|
