metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
model-index:
- name: whisper-tiny-hi
results: []
whisper-tiny-hi
This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.0004
- eval_wer: 93.3333
- eval_runtime: 4.6316
- eval_samples_per_second: 1.08
- eval_steps_per_second: 0.216
- epoch: 333.33
- step: 1000
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: 8
- 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: 4000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2