|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: openai/whisper-large-v2 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: whisper-large-v2-3swissdatasets |
|
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-v2-3swissdatasets |
|
|
|
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: 0.2758 |
|
- Wer: 17.7832 |
|
|
|
## 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: 5e-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: 500 |
|
- training_steps: 6000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:------:|:----:|:---------------:|:-------:| |
|
| 0.5575 | 0.0727 | 1000 | 0.6201 | 35.9145 | |
|
| 0.4618 | 0.1454 | 2000 | 0.5084 | 30.6525 | |
|
| 0.3571 | 0.2181 | 3000 | 0.4122 | 25.1587 | |
|
| 0.3845 | 0.2908 | 4000 | 0.3702 | 23.1700 | |
|
| 0.2471 | 0.3635 | 5000 | 0.3127 | 19.8575 | |
|
| 0.2415 | 0.4362 | 6000 | 0.2758 | 17.7832 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.1 |
|
- Pytorch 2.3.1+cu118 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.19.1 |
|
|
