metadata
language:
- en
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: openai/whisper-tiny
results: []
openai/whisper-tiny
This model is a fine-tuned version of openai/whisper-tiny on the pphuc25/EngMed dataset. It achieves the following results on the evaluation set:
- Loss: 2.1885
- Wer: 64.3381
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: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.2506 | 1.0 | 2506 | 1.8234 | 68.3468 |
| 0.8111 | 2.0 | 5012 | 1.8613 | 63.4767 |
| 0.4577 | 3.0 | 7518 | 1.9671 | 71.6598 |
| 0.2581 | 4.0 | 10024 | 2.1055 | 63.3726 |
| 0.1261 | 5.0 | 12530 | 2.1885 | 64.3381 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1