|
|
--- |
|
|
language: |
|
|
- nl |
|
|
license: apache-2.0 |
|
|
base_model: openai/whisper-large-v2 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- wer |
|
|
model-index: |
|
|
- name: Whisper Large V2 |
|
|
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 Large V2 |
|
|
|
|
|
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3167 |
|
|
- Wer: 11.6330 |
|
|
|
|
|
## 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: 3e-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: 20 |
|
|
- num_epochs: 5 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:-------:| |
|
|
| 0.6772 | 0.71 | 30 | 0.3209 | 16.8396 | |
|
|
| 0.2613 | 1.43 | 60 | 0.3041 | 12.8163 | |
|
|
| 0.1683 | 2.14 | 90 | 0.2908 | 11.8332 | |
|
|
| 0.0777 | 2.86 | 120 | 0.2916 | 10.8138 | |
|
|
| 0.0428 | 3.57 | 150 | 0.2965 | 11.7786 | |
|
|
| 0.0228 | 4.29 | 180 | 0.3114 | 11.8150 | |
|
|
| 0.0107 | 5.0 | 210 | 0.3167 | 11.6330 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.38.0.dev0 |
|
|
- Pytorch 2.1.0+cu121 |
|
|
- Datasets 2.14.6 |
|
|
- Tokenizers 0.15.0 |
|
|
|
