metadata
language:
- en
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- Jzuluaga/atcosim_corpus
metrics:
- wer
model-index:
- name: bhattasp/w_f1_v2v_tiny
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: atcosim
type: Jzuluaga/atcosim_corpus
args: 'config: en, split: test'
metrics:
- name: Wer
type: wer
value: 11.566999381680064
bhattasp/w_f1_v2v_tiny
This model is a fine-tuned version of openai/whisper-tiny on the atcosim dataset. It achieves the following results on the evaluation set:
- Loss: 0.2832
- Wer: 11.5670
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: 2000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.0131 | 3.1949 | 1000 | 0.2830 | 11.9115 |
0.0012 | 6.3898 | 2000 | 0.2832 | 11.5670 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1