metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
model-index:
- name: whisper-tiny
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: 0.2926102502979738
whisper-tiny
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: 0.6649
- Wer Ortho: 0.2984
- Wer: 0.2926
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: 750
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.3212 | 3.57 | 100 | 0.4962 | 0.3115 | 0.2974 |
| 0.0362 | 7.14 | 200 | 0.5397 | 0.3096 | 0.2980 |
| 0.0045 | 10.71 | 300 | 0.5860 | 0.2984 | 0.2878 |
| 0.0015 | 14.29 | 400 | 0.6235 | 0.3077 | 0.3027 |
| 0.0015 | 17.86 | 500 | 0.6388 | 0.2984 | 0.2938 |
| 0.0006 | 21.43 | 600 | 0.6467 | 0.2996 | 0.2962 |
| 0.0006 | 25.0 | 700 | 0.6649 | 0.2984 | 0.2926 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.1
- Tokenizers 0.13.3