metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: whisper-base-kn
results: []
whisper-base-kn
This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.1974
- eval_wer: 30.8790
- eval_runtime: 69.6684
- eval_samples_per_second: 1.435
- eval_steps_per_second: 0.029
- epoch: 2.28
- step: 5000
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: 96
- eval_batch_size: 64
- 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
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2