metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- common_voice_11_0
metrics:
- wer
model-index:
- name: openai/whisper-small
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_11_0
type: common_voice_11_0
config: ar
split: test
args: ar
metrics:
- name: Wer
type: wer
value: 44.976586
openai/whisper-small
This model is a fine-tuned version of openai/whisper-small on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.322550
- Wer: 44.976586
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: train_batch_size=16 gradient_accumulation_steps=1 learning_rate=1e-5 warmup_steps=500 max_steps=4000 gradient_checkpointing=True fp16=True evaluation_strategy="steps" save_steps=1000 eval_steps=1000 logging_steps=25 metric_for_best_model="wer"
Training results
| Training Loss | Step | Validation Loss | Wer |
|---|---|---|---|
| 0.2811 | 1000 | 0.393018 | 53.778349 |
| 0.2356 | 2000 | 0.348794 | 47.793591 |
| 0.1705 | 3000 | 0.332207 | 45.758883 |
| 0.1476 | 4000 | 0.322550 | 44.976586 |