metadata
language:
- eu
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_13_0
metrics:
- wer
model-index:
- name: Whisper Small Basque
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: mozilla-foundation/common_voice_13_0 eu
type: mozilla-foundation/common_voice_13_0
config: eu
split: test
args: eu
metrics:
- name: Wer
type: wer
value: 13.996111628660538
Whisper Small Basque
This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_13_0 eu dataset. It achieves the following results on the evaluation set:
- Loss: 0.2256
- Wer: 13.9961
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4198 | 0.2 | 1000 | 0.4102 | 28.3487 |
| 0.2547 | 0.4 | 2000 | 0.3142 | 21.6432 |
| 0.2145 | 0.6 | 3000 | 0.2610 | 17.5159 |
| 0.0828 | 1.14 | 4000 | 0.2388 | 15.3003 |
| 0.0729 | 1.34 | 5000 | 0.2256 | 13.9961 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2