metadata
language:
- hi
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
model-index:
- name: Whisper Small ko-elder70 - syp1229
results: []
Whisper Small ko-elder70 - syp1229
This model is a fine-tuned version of openai/whisper-small on the aihub elder over 70 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1961
- Cer: 4.5511
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: 2e-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
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.2246 | 0.3 | 100 | 0.2532 | 6.3965 |
| 0.213 | 0.59 | 200 | 0.2291 | 6.2897 |
| 0.1986 | 0.89 | 300 | 0.2037 | 5.5361 |
| 0.0683 | 1.18 | 400 | 0.1912 | 4.7410 |
| 0.0691 | 1.48 | 500 | 0.1967 | 5.0139 |
| 0.0782 | 1.78 | 600 | 0.1999 | 5.0555 |
| 0.0219 | 2.07 | 700 | 0.1907 | 4.9843 |
| 0.0193 | 2.37 | 800 | 0.1918 | 4.5986 |
| 0.0283 | 2.66 | 900 | 0.1966 | 4.8003 |
| 0.0163 | 2.96 | 1000 | 0.1904 | 4.4740 |
| 0.0083 | 3.25 | 1100 | 0.1958 | 4.3909 |
| 0.0039 | 3.55 | 1200 | 0.1983 | 4.4562 |
| 0.0043 | 3.85 | 1300 | 0.1944 | 4.4858 |
| 0.0029 | 4.14 | 1400 | 0.1941 | 4.4384 |
| 0.0027 | 4.44 | 1500 | 0.1981 | 4.5571 |
| 0.003 | 4.73 | 1600 | 0.1961 | 4.5511 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3