metadata
language:
- kr
license: apache-2.0
base_model: openai/whisper-large-v2
tags:
- generated_from_trainer
datasets:
- Jungwonchang/ksponspeech
metrics:
- wer
model-index:
- name: Whisper large-v2, KsponSpeech
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: KsponSpeech
type: Jungwonchang/ksponspeech
config: dev
split: validation
args: dev
metrics:
- name: Wer
type: wer
value: 42.225687000584685
Whisper large-v2, KsponSpeech
This model is a fine-tuned version of openai/whisper-large-v2 on the KsponSpeech dataset. It achieves the following results on the evaluation set:
- Loss: 0.2946
- Wer: 42.2257
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: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3315 | 0.25 | 500 | 0.3446 | 41.5319 |
| 0.3204 | 0.5 | 1000 | 0.3229 | 37.7003 |
| 0.2967 | 0.75 | 1500 | 0.3054 | 38.3980 |
| 0.2859 | 1.0 | 2000 | 0.2946 | 42.2257 |
Framework versions
- Transformers 4.31.0
- Pytorch 1.12.1+cu116
- Datasets 2.14.0
- Tokenizers 0.12.1