|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: whisper-large-et-clinic |
|
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-et-clinic |
|
|
|
This model is a fine-tuned version of [agnesluhtaru/whisper-large-et-ERR2020-v2](https://huggingface.co/agnesluhtaru/whisper-large-et-ERR2020-v2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3862 |
|
- Wer: 15.5413 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 200 |
|
- training_steps: 2000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:| |
|
| 0.0278 | 4.03 | 500 | 0.2986 | 16.9940 | |
|
| 0.0037 | 8.06 | 1000 | 0.3383 | 16.1774 | |
|
| 0.0017 | 12.1 | 1500 | 0.3619 | 15.8035 | |
|
| 0.0008 | 16.13 | 2000 | 0.3862 | 15.5413 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0.dev0 |
|
- Pytorch 1.12.1+rocm5.1.1 |
|
- Datasets 2.7.1.dev0 |
|
- Tokenizers 0.13.2 |
|
|
