metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-tiny-kor-16k-hf_ver3
results: []
whisper-tiny-kor-16k-hf_ver3
This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.7967
- Wer: 932.0
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: 5e-05
- train_batch_size: 128
- 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
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 1.0 | 1 | 2.7967 | 932.0 |
| No log | 2.0 | 2 | 2.7967 | 932.0 |
| No log | 3.0 | 3 | 2.7967 | 932.0 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.0.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.0