|
--- |
|
library_name: transformers |
|
language: |
|
- hi |
|
license: apache-2.0 |
|
base_model: openai/whisper-small |
|
tags: |
|
- hf-asr-leaderboard |
|
- generated_from_trainer |
|
datasets: |
|
- aihub_adult_baseline |
|
model-index: |
|
- name: whisper-small-E50_freq_pause_speed |
|
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-E50_freq_pause_speed |
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the aihub old adult freq speed pause changed dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1725 |
|
- Cer: 5.0634 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 16 |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 50 |
|
- num_epochs: 2 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Cer | |
|
|:-------------:|:------:|:----:|:---------------:|:------:| |
|
| 0.3013 | 0.1289 | 100 | 0.2517 | 6.4438 | |
|
| 0.1815 | 0.2579 | 200 | 0.2203 | 6.0385 | |
|
| 0.1893 | 0.3868 | 300 | 0.2076 | 5.6450 | |
|
| 0.1646 | 0.5158 | 400 | 0.1988 | 5.5275 | |
|
| 0.1377 | 0.6447 | 500 | 0.1969 | 5.4453 | |
|
| 0.1279 | 0.7737 | 600 | 0.1852 | 5.1809 | |
|
| 0.1254 | 0.9026 | 700 | 0.1795 | 4.9107 | |
|
| 0.0701 | 1.0309 | 800 | 0.1769 | 4.8990 | |
|
| 0.0586 | 1.1599 | 900 | 0.1805 | 4.9518 | |
|
| 0.0588 | 1.2888 | 1000 | 0.1763 | 5.2044 | |
|
| 0.0568 | 1.4178 | 1100 | 0.1782 | 5.2103 | |
|
| 0.0487 | 1.5467 | 1200 | 0.1737 | 4.8285 | |
|
| 0.0526 | 1.6757 | 1300 | 0.1745 | 5.3571 | |
|
| 0.0439 | 1.8046 | 1400 | 0.1730 | 7.2721 | |
|
| 0.0476 | 1.9336 | 1500 | 0.1725 | 5.0634 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.47.0.dev0 |
|
- Pytorch 2.5.0+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|
