metadata
language:
- en
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- Shiry/ATC_combined
metrics:
- wer
model-index:
- name: Whisper Small ATC - ATCText
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: ATC
type: Shiry/ATC_combined
args: 'split: test'
metrics:
- name: Wer
type: wer
value: 9.924699404882393
Whisper Small ATC - ATCText
This model is a fine-tuned version of openai/whisper-small on the ATC dataset. It achieves the following results on the evaluation set:
- Loss: 0.2696
- Wer: 9.9247
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2728 | 0.84 | 1000 | 0.3054 | 13.2221 |
| 0.1259 | 1.69 | 2000 | 0.2615 | 10.4611 |
| 0.0558 | 2.53 | 3000 | 0.2588 | 9.9267 |
| 0.0316 | 3.38 | 4000 | 0.2690 | 9.8680 |
| 0.0136 | 4.22 | 5000 | 0.2696 | 9.9247 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2
- Datasets 2.18.0
- Tokenizers 0.15.2