metadata
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- google/fleurs
metrics:
- wer
model-index:
- name: Whisper Small Amharic FLEURS
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: google/fleurs am_et
type: google/fleurs
config: am_et
split: validation
args: am_et
metrics:
- name: Wer
type: wer
value: 100
Whisper Small Amharic FLEURS
This model is a fine-tuned version of openai/whisper-small on the google/fleurs am_et dataset. It achieves the following results on the evaluation set:
- Loss: 6.8012
- Wer: 100.0
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: 64
- eval_batch_size: 32
- 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 |
|---|---|---|---|---|
| 0.9013 | 100.0 | 100 | 2.7051 | 276.0 |
| 0.0002 | 200.0 | 200 | 3.7415 | 334.6667 |
| 0.0001 | 300.0 | 300 | 3.8402 | 117.3333 |
| 0.0001 | 400.0 | 400 | 3.8931 | 340.0 |
| 0.0001 | 500.0 | 500 | 4.0671 | 397.3333 |
| 0.0001 | 600.0 | 600 | 4.2844 | 137.3333 |
| 0.0 | 700.0 | 700 | 4.4697 | 289.3333 |
| 0.0 | 800.0 | 800 | 4.6278 | 449.3333 |
| 0.0 | 900.0 | 900 | 4.7794 | 678.6667 |
| 0.0405 | 1000.0 | 1000 | 4.6769 | 261.3333 |
| 0.0002 | 1100.0 | 1100 | 5.4995 | 100.0 |
| 0.0002 | 1200.0 | 1200 | 6.0033 | 100.0 |
| 0.0002 | 1300.0 | 1300 | 6.2884 | 100.0 |
| 0.0002 | 1400.0 | 1400 | 6.4744 | 100.0 |
| 0.0002 | 1500.0 | 1500 | 6.5964 | 100.0 |
| 0.0001 | 1600.0 | 1600 | 6.6792 | 100.0 |
| 0.0001 | 1700.0 | 1700 | 6.7370 | 100.0 |
| 0.0001 | 1800.0 | 1800 | 6.7735 | 100.0 |
| 0.0001 | 1900.0 | 1900 | 6.7958 | 100.0 |
| 0.0001 | 2000.0 | 2000 | 6.8012 | 100.0 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2