metadata
language:
- ko
license: apache-2.0
base_model: openai/whisper-medium
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- Marcusxx/CHUNGNAM_FM_Addresses
model-index:
- name: CHUNGNAM_FM_AddressesM_model
results: []
CHUNGNAM_FM_AddressesM_model
This model is a fine-tuned version of openai/whisper-medium on the Marcusxx/CHUNGNAM_FM_Addresses dataset. It achieves the following results on the evaluation set:
- Loss: 0.0028
- Cer: 0.3136
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: 100
- training_steps: 10000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0183 | 0.6906 | 1000 | 0.0229 | 12.0681 |
| 0.0122 | 1.3812 | 2000 | 0.0123 | 6.4812 |
| 0.001 | 2.0718 | 3000 | 0.0069 | 1.0985 |
| 0.0024 | 2.7624 | 4000 | 0.0048 | 0.6624 |
| 0.0022 | 3.4530 | 5000 | 0.0053 | 0.1633 |
| 0.0011 | 4.1436 | 6000 | 0.0033 | 0.0983 |
| 0.0002 | 4.8343 | 7000 | 0.0029 | 2.2785 |
| 0.0002 | 5.5249 | 8000 | 0.0029 | 0.8869 |
| 0.0 | 6.2155 | 9000 | 0.0033 | 0.3470 |
| 0.0 | 6.9061 | 10000 | 0.0028 | 0.3136 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.2.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1