|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
base_model: openai/whisper-small |
|
datasets: |
|
- Jzuluaga/atcosim_corpus |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: Whisper Base ATCOSIM |
|
results: |
|
- task: |
|
type: automatic-speech-recognition |
|
name: Automatic Speech Recognition |
|
dataset: |
|
name: atcosim_corpus |
|
type: Jzuluaga/atcosim_corpus |
|
args: 'config: en, split: test' |
|
metrics: |
|
- type: wer |
|
value: 7.2040707016604175 |
|
name: Wer |
|
--- |
|
|
|
<!-- 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 Base ATCOSIM |
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the atcosim_corpus dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0468 |
|
- Wer: 7.2041 |
|
|
|
## 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: 1000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:------:|:----:|:---------------:|:-------:| |
|
| 1.6033 | 0.2092 | 100 | 1.3602 | 78.1066 | |
|
| 0.6161 | 0.4184 | 200 | 0.5993 | 21.7930 | |
|
| 0.1103 | 0.6276 | 300 | 0.1273 | 14.7362 | |
|
| 0.0631 | 0.8368 | 400 | 0.0865 | 13.7587 | |
|
| 0.0369 | 1.0460 | 500 | 0.0763 | 11.9644 | |
|
| 0.0198 | 1.2552 | 600 | 0.0644 | 16.8117 | |
|
| 0.0369 | 1.4644 | 700 | 0.0599 | 10.4379 | |
|
| 0.0272 | 1.6736 | 800 | 0.0518 | 12.1920 | |
|
| 0.0202 | 1.8828 | 900 | 0.0473 | 8.4159 | |
|
| 0.0064 | 2.0921 | 1000 | 0.0468 | 7.2041 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.0.dev0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
