metadata
language:
- pt
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
model-index:
- name: Whisper Tiny en - thiagoms
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 13
type: PolyAI/minds14
config: en-US
split: train
args: en-US
metrics:
- name: Wer
type: wer
value: 0.3654073199527745
Whisper Tiny en - thiagoms
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 13 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7762
- Wer Ortho: 0.3658
- Wer: 0.3654
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: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0007 | 17.86 | 500 | 0.6431 | 0.3578 | 0.3548 |
| 0.0002 | 35.71 | 1000 | 0.7066 | 0.3664 | 0.3648 |
| 0.0001 | 53.57 | 1500 | 0.7466 | 0.3683 | 0.3672 |
| 0.0001 | 71.43 | 2000 | 0.7762 | 0.3658 | 0.3654 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.0+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3