|
---
|
|
license: apache-2.0
|
|
base_model: openai/whisper-small.en
|
|
tags:
|
|
- generated_from_trainer
|
|
metrics:
|
|
- wer
|
|
model-index:
|
|
- name: whisper-small.en-atcosim
|
|
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. -->
|
|
|
|
# whisper-small.en-atcosim
|
|
|
|
This model is a fine-tuned version of [openai/whisper-small.en](https://huggingface.co/openai/whisper-small.en) on an unknown dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.0571
|
|
- Wer: 2.2921
|
|
|
|
## 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: 128
|
|
- eval_batch_size: 128
|
|
- seed: 42
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
- lr_scheduler_type: linear
|
|
- lr_scheduler_warmup_steps: 10
|
|
- num_epochs: 100
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
|
| 0.2554 | 8.33 | 500 | 0.0455 | 2.2087 |
|
|
| 0.0004 | 16.67 | 1000 | 0.0483 | 2.3384 |
|
|
| 0.0002 | 25.0 | 1500 | 0.0496 | 2.3847 |
|
|
| 0.0001 | 33.33 | 2000 | 0.0513 | 2.3430 |
|
|
| 0.0 | 41.67 | 2500 | 0.0527 | 2.3477 |
|
|
| 0.0 | 50.0 | 3000 | 0.0538 | 2.3430 |
|
|
| 0.0 | 58.33 | 3500 | 0.0547 | 2.3384 |
|
|
| 0.0 | 66.67 | 4000 | 0.0555 | 2.3384 |
|
|
| 0.0 | 75.0 | 4500 | 0.0561 | 2.3338 |
|
|
| 0.0 | 83.33 | 5000 | 0.0566 | 2.3152 |
|
|
| 0.0 | 91.67 | 5500 | 0.0570 | 2.2967 |
|
|
| 0.0 | 100.0 | 6000 | 0.0571 | 2.2921 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.36.2
|
|
- Pytorch 2.1.2
|
|
- Datasets 2.15.0
|
|
- Tokenizers 0.15.0
|
|
|
