metadata
library_name: transformers
language:
- en
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- FreeSound
metrics:
- wer
model-index:
- name: Whisper Tiny En - FreeSound based captions test
results: []
Whisper Tiny En - FreeSound based captions test
This model is a fine-tuned version of openai/whisper-tiny on the FreeSound Audio dataset. It achieves the following results on the evaluation set:
- Loss: 3.8548
- Wer: 98.5500
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: 10
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 5.2273 | 0.6098 | 25 | 4.9782 | 101.4246 |
| 4.0984 | 1.2195 | 50 | 4.1433 | 100.8904 |
| 3.8301 | 1.8293 | 75 | 3.9157 | 99.3132 |
| 3.7081 | 2.4390 | 100 | 3.8548 | 98.5500 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.1.0+cu118
- Datasets 3.0.1
- Tokenizers 0.20.1