metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
model-index:
- name: whisper-tiny-minds14-en-us
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: PolyAI/minds14
type: PolyAI/minds14
config: en-US
split: train
args: en-US
metrics:
- name: Wer
type: wer
value: 0.35400516795865633
whisper-tiny-minds14-en-us
This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7195
- Wer Ortho: 0.3560
- Wer: 0.3540
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: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 1.8452 | 1.79 | 50 | 0.8160 | 0.3890 | 0.3534 |
| 0.3172 | 3.57 | 100 | 0.5341 | 0.3573 | 0.3547 |
| 0.1191 | 5.36 | 150 | 0.5525 | 0.3284 | 0.3217 |
| 0.0363 | 7.14 | 200 | 0.6061 | 0.3472 | 0.3456 |
| 0.0099 | 8.93 | 250 | 0.6240 | 0.3546 | 0.3540 |
| 0.0036 | 10.71 | 300 | 0.6596 | 0.3560 | 0.3527 |
| 0.0019 | 12.5 | 350 | 0.6777 | 0.3513 | 0.3508 |
| 0.0012 | 14.29 | 400 | 0.6946 | 0.3540 | 0.3527 |
| 0.0009 | 16.07 | 450 | 0.7079 | 0.3526 | 0.3514 |
| 0.0007 | 17.86 | 500 | 0.7195 | 0.3560 | 0.3540 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0