|
--- |
|
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: 0.3485 |
|
- Wer: 12.5880 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:| |
|
| 0.5418 | 0.49 | 30 | 0.3376 | 12.7246 | |
|
| 0.2735 | 0.98 | 60 | 0.3104 | 14.0380 | |
|
| 0.1441 | 1.48 | 90 | 0.3110 | 14.0380 | |
|
| 0.1241 | 1.97 | 120 | 0.3036 | 12.1572 | |
|
| 0.0581 | 2.46 | 150 | 0.3239 | 11.6528 | |
|
| 0.0536 | 2.95 | 180 | 0.3266 | 13.2500 | |
|
| 0.0274 | 3.44 | 210 | 0.3464 | 12.2307 | |
|
| 0.0224 | 3.93 | 240 | 0.3380 | 12.5775 | |
|
| 0.0119 | 4.43 | 270 | 0.3473 | 12.7036 | |
|
| 0.0087 | 4.92 | 300 | 0.3485 | 12.5880 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.0.dev0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.15.0 |
|
|
