metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- common_voice_16_1
metrics:
- wer
model-index:
- name: output1
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_16_1
type: common_voice_16_1
config: ko
split: test
args: ko
metrics:
- name: Wer
type: wer
value: 140.13953488372093
output1
This model is a fine-tuned version of openai/whisper-tiny on the common_voice_16_1 dataset. It achieves the following results on the evaluation set:
- Loss: 1.0385
- Wer: 140.1395
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: 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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0034 | 25.0 | 1000 | 0.9055 | 100.2326 |
| 0.001 | 50.0 | 2000 | 0.9852 | 113.7674 |
| 0.0005 | 75.0 | 3000 | 1.0243 | 139.9070 |
| 0.0004 | 100.0 | 4000 | 1.0385 | 140.1395 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.1+cpu
- Datasets 3.0.0
- Tokenizers 0.19.1