|
--- |
|
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: 0.1401 |
|
- Wer: 5.5491 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 0.4119 | 0.38 | 30 | 0.1653 | 7.8245 | |
|
| 0.1737 | 0.75 | 60 | 0.1446 | 5.7271 | |
|
| 0.1437 | 1.12 | 90 | 0.1420 | 6.7487 | |
|
| 0.0785 | 1.5 | 120 | 0.1317 | 5.1931 | |
|
| 0.0707 | 1.88 | 150 | 0.1309 | 6.2379 | |
|
| 0.0496 | 2.25 | 180 | 0.1369 | 5.9670 | |
|
| 0.0318 | 2.62 | 210 | 0.1316 | 6.0367 | |
|
| 0.0341 | 3.0 | 240 | 0.1290 | 5.5568 | |
|
| 0.0166 | 3.38 | 270 | 0.1339 | 4.9532 | |
|
| 0.0147 | 3.75 | 300 | 0.1353 | 5.4949 | |
|
| 0.0109 | 4.12 | 330 | 0.1365 | 5.6342 | |
|
| 0.0072 | 4.5 | 360 | 0.1402 | 5.4640 | |
|
| 0.0071 | 4.88 | 390 | 0.1401 | 5.5491 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.0.dev0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.15.0 |
|
|
