Whisper Small Darija
This model is a fine-tuned version of openai/whisper-small on the DatasetDarijaTest dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.7074
- eval_runtime: 57.1463
- eval_samples_per_second: 2.625
- eval_steps_per_second: 0.332
- epoch: 1.9324
- step: 800
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 200
- num_epochs: 2
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.44.0
- Pytorch 2.2.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
Model tree for Fahd1199/MergeV2-FineTuned
Base model
openai/whisper-small