Whisper Base Ha - Eldad Akhaumere
This model is a fine-tuned version of openai/whisper-base on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:
- eval_loss: 2.5009
- eval_wer_ortho: 106.2891
- eval_wer: 104.9243
- eval_runtime: 168.7552
- eval_samples_per_second: 3.911
- eval_steps_per_second: 0.249
- epoch: 12.7389
- step: 2000
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- num_epochs: 15.0
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 39
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for eldad-akhaumere/whisper-base-ha
Base model
openai/whisper-base