metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
model-index:
- name: whisper-tiny-minds14
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: 0.28512396694214875
whisper-tiny-minds14
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: 0.7381
- Wer Ortho: 0.2850
- Wer: 0.2851
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 0
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.9105 | 1.7857 | 50 | 0.6418 | 0.4115 | 0.3937 |
| 0.2535 | 3.5714 | 100 | 0.5773 | 0.3337 | 0.3164 |
| 0.0887 | 5.3571 | 150 | 0.6295 | 0.3368 | 0.3182 |
| 0.0288 | 7.1429 | 200 | 0.6449 | 0.3381 | 0.3211 |
| 0.0198 | 8.9286 | 250 | 0.6932 | 0.4170 | 0.4203 |
| 0.0092 | 10.7143 | 300 | 0.6835 | 0.3152 | 0.3058 |
| 0.0134 | 12.5 | 350 | 0.7404 | 0.3288 | 0.3264 |
| 0.0096 | 14.2857 | 400 | 0.7067 | 0.3374 | 0.3312 |
| 0.0073 | 16.0714 | 450 | 0.7303 | 0.3122 | 0.3081 |
| 0.0056 | 17.8571 | 500 | 0.7381 | 0.2850 | 0.2851 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1
- Datasets 3.0.0
- Tokenizers 0.19.1