metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
base_model: openai/whisper-tiny
model-index:
- name: whisper-tiny-finetuned-minds14
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: MINDS14
type: PolyAI/minds14
metrics:
- type: wer
value: 0.34993849938499383
name: Wer
whisper-tiny-finetuned-minds14
This model is a fine-tuned version of openai/whisper-tiny on the MINDS14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6435
- Wer Ortho: 0.3797
- Wer: 0.3499
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
---|---|---|---|---|---|
4.995 | 1.0 | 29 | 2.9879 | 0.5425 | 0.4127 |
2.1634 | 2.0 | 58 | 0.8084 | 0.4382 | 0.3936 |
0.6659 | 3.0 | 87 | 0.6268 | 0.4144 | 0.3678 |
0.3865 | 4.0 | 116 | 0.5987 | 0.3880 | 0.3561 |
0.2428 | 5.0 | 145 | 0.6005 | 0.3990 | 0.3659 |
0.1734 | 6.0 | 174 | 0.6162 | 0.3906 | 0.3573 |
0.0965 | 7.0 | 203 | 0.6221 | 0.3893 | 0.3561 |
0.0682 | 8.0 | 232 | 0.6320 | 0.3803 | 0.3493 |
0.0473 | 9.0 | 261 | 0.6411 | 0.3797 | 0.3493 |
0.0476 | 10.0 | 290 | 0.6435 | 0.3797 | 0.3499 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3