metadata
language:
- ko
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- kr_dialect_speech
metrics:
- wer
model-index:
- name: Whisper Small Ko(Gyungsang dialect) - p4b
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: KR Dialect Speech - gyungsang
type: kr_dialect_speech
config: gyungsang
split: validation
args: gyungsang
metrics:
- name: Wer
type: wer
value: 15.930018416206263
Whisper Small Ko(Gyungsang dialect) - p4b
This model is a fine-tuned version of openai/whisper-small on the KR Dialect Speech - gyungsang dataset. It achieves the following results on the evaluation set:
- Loss: 0.2017
- Wer: 15.9300
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: 5e-07
- train_batch_size: 96
- eval_batch_size: 64
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5909 | 0.2 | 1000 | 0.4133 | 211.6022 |
| 0.3612 | 0.4 | 2000 | 0.2137 | 16.9429 |
| 0.5373 | 0.6 | 3000 | 0.2063 | 15.8379 |
| 0.2909 | 0.8 | 4000 | 0.2012 | 15.8379 |
| 0.3317 | 1.0 | 5000 | 0.2017 | 15.9300 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.14.0.dev20221208+cu116
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2