Whisper Tiny FT NL_bs32
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 13.0, voxpopuli dataset. It achieves the following results on the evaluation set:
- Loss: 0.2896
- Wer: 97.7034
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: 32
- eval_batch_size: 16
- 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: 10000
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.3004 | 0.1 | 1000 | 0.3763 | 82.0359 |
0.1669 | 1.07 | 2000 | 0.3136 | 53.1062 |
0.1276 | 2.03 | 3000 | 0.2915 | 64.4126 |
0.1146 | 2.13 | 4000 | 0.3259 | 60.0555 |
0.0758 | 3.1 | 5000 | 0.3042 | 73.8444 |
0.059 | 4.06 | 6000 | 0.3088 | 83.9768 |
0.0554 | 5.03 | 7000 | 0.2905 | 81.0178 |
0.0503 | 5.13 | 8000 | 0.2877 | 88.2464 |
0.0499 | 6.1 | 9000 | 0.3116 | 91.4979 |
0.0493 | 7.06 | 10000 | 0.2896 | 97.7034 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.1
- Datasets 2.14.7
- Tokenizers 0.14.1
- Downloads last month
- 8
Finetuned from
Dataset used to train Jaspernl/whisper-tiny-ft-nl_ortho
Evaluation results
- Wer on Common Voice 13.0, voxpopulitest set self-reported97.703