metadata
language:
- id
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_9_0
metrics:
- wer
model-index:
- name: Whisper Small Indonesian
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: mozilla-foundation/common_voice_9_0 id
type: mozilla-foundation/common_voice_9_0
config: id
split: test
args: id
metrics:
- name: Wer
type: wer
value: 32.55118472509777
Whisper Small Indonesian
This model is a fine-tuned version of openai/whisper-tiny on the mozilla-foundation/common_voice_9_0 id dataset. It achieves the following results on the evaluation set:
- Loss: 0.4997
- Wer: 32.5512
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: 2
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.7055 | 0.48 | 1000 | 0.6329 | 42.1072 |
| 0.5685 | 0.97 | 2000 | 0.5515 | 35.8638 |
| 0.3807 | 1.45 | 3000 | 0.5232 | 34.0189 |
| 0.3766 | 1.94 | 4000 | 0.4993 | 32.6708 |
| 0.3567 | 2.42 | 5000 | 0.4997 | 32.5512 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3