Whisper Large v3 — Libyan Arabic Dialect
This model is a fine-tuned version of openai/whisper-large-v3 on the Custom Libyan Arabic podcast — 258 manually transcribed clips dataset. It achieves the following results on the evaluation set:
- Loss: 0.5756
- Wer: 31.3595
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: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAFACTOR and the args are: No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 300
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2901 | 6.6897 | 100 | 0.4252 | 30.0250 |
| 0.0239 | 13.3448 | 200 | 0.5545 | 30.4420 |
| 0.0146 | 20.0 | 300 | 0.5756 | 31.3595 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 95
Model tree for Rhaodgh/whisper-large-libyan
Base model
openai/whisper-large-v3