metadata
language:
- ate
license: apache-2.0
base_model: openai/whisper-base
tags:
- whisper-event
- generated_from_trainer
datasets:
- tericlabs
metrics:
- wer
model-index:
- name: Whisper base ateso
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Sunbird
type: tericlabs
metrics:
- name: Wer
type: wer
value: 27.710843373493976
Whisper base ateso
This model is a fine-tuned version of openai/whisper-base on the Sunbird dataset. It achieves the following results on the evaluation set:
- Loss: 0.5293
- Wer: 27.7108
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: 1000
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4597 | 3.5 | 1000 | 0.5186 | 32.1285 |
| 0.1812 | 6.99 | 2000 | 0.4394 | 26.7738 |
| 0.0429 | 10.49 | 3000 | 0.4765 | 26.7738 |
| 0.016 | 13.99 | 4000 | 0.5157 | 27.3092 |
| 0.0053 | 17.48 | 5000 | 0.5293 | 27.7108 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2