metadata
license: apache-2.0
tags:
- generated_from_trainer
base_model: openai/whisper-small
datasets:
- verba_lex_voice
metrics:
- wer
model-index:
- name: verbalex-ar
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: verba_lex_voice
type: verba_lex_voice
config: ar
split: test
args: ar
metrics:
- type: wer
value: 3.481475113900111
name: Wer
verbalex-ar
This model is a fine-tuned version of openai/whisper-small on the verba_lex_voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.0880
- Wer: 3.4815
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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0015 | 5.2356 | 1000 | 0.0809 | 3.6620 |
| 0.0002 | 10.4712 | 2000 | 0.0845 | 3.5073 |
| 0.0001 | 15.7068 | 3000 | 0.0865 | 3.5245 |
| 0.0001 | 20.9424 | 4000 | 0.0877 | 3.5073 |
| 0.0001 | 26.1780 | 5000 | 0.0880 | 3.4815 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.1.2
- Datasets 2.16.0
- Tokenizers 0.19.1