|
--- |
|
language: |
|
- hi |
|
license: apache-2.0 |
|
base_model: openai/whisper-small |
|
tags: |
|
- hf-asr-leaderboard |
|
- generated_from_trainer |
|
model-index: |
|
- name: Whisper Small ko-Yfreq - syp1229 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# Whisper Small ko-Yfreq - syp1229 |
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the aihub Y dialogue dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1951 |
|
- Cer: 0.0822 |
|
|
|
## 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: 100 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Cer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 0.2218 | 0.3 | 100 | 0.2452 | 0.0622 | |
|
| 0.2261 | 0.59 | 200 | 0.2389 | 0.0653 | |
|
| 0.2032 | 0.89 | 300 | 0.2079 | 0.0554 | |
|
| 0.0821 | 1.18 | 400 | 0.2152 | 0.0630 | |
|
| 0.0763 | 1.48 | 500 | 0.2025 | 0.0520 | |
|
| 0.0778 | 1.78 | 600 | 0.1997 | 0.0611 | |
|
| 0.0216 | 2.07 | 700 | 0.1918 | 0.0609 | |
|
| 0.0226 | 2.37 | 800 | 0.1884 | 0.0663 | |
|
| 0.0289 | 2.66 | 900 | 0.1940 | 0.2490 | |
|
| 0.0212 | 2.96 | 1000 | 0.1925 | 0.1068 | |
|
| 0.0075 | 3.25 | 1100 | 0.1966 | 0.0615 | |
|
| 0.0044 | 3.55 | 1200 | 0.1986 | 0.0629 | |
|
| 0.0051 | 3.85 | 1300 | 0.1950 | 0.1097 | |
|
| 0.003 | 4.14 | 1400 | 0.1929 | 0.0689 | |
|
| 0.0029 | 4.44 | 1500 | 0.1958 | 0.0774 | |
|
| 0.0029 | 4.73 | 1600 | 0.1951 | 0.0822 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0.dev0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
