|
--- |
|
license: apache-2.0 |
|
base_model: openai/whisper-small |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- google/fleurs |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: whisper-small-af-ZA |
|
results: |
|
- task: |
|
name: Automatic Speech Recognition |
|
type: automatic-speech-recognition |
|
dataset: |
|
name: google/fleurs |
|
type: google/fleurs |
|
config: af_za |
|
split: train+validation |
|
args: af_za |
|
metrics: |
|
- name: Wer |
|
type: wer |
|
value: 0.36644093303235514 |
|
--- |
|
|
|
<!-- 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-small-af-ZA |
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the google/fleurs dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5728 |
|
- Wer Ortho: 0.3943 |
|
- Wer: 0.3664 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant_with_warmup |
|
- lr_scheduler_warmup_steps: 5 |
|
- training_steps: 2000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:| |
|
| 0.7731 | 1.45 | 100 | 0.7280 | 0.3863 | 0.3740 | |
|
| 0.2103 | 2.9 | 200 | 0.5116 | 0.3859 | 0.3661 | |
|
| 0.0633 | 4.35 | 300 | 0.4967 | 0.3008 | 0.2810 | |
|
| 0.0249 | 5.8 | 400 | 0.5003 | 0.3477 | 0.3299 | |
|
| 0.0143 | 7.25 | 500 | 0.5191 | 0.3660 | 0.3510 | |
|
| 0.0053 | 8.7 | 600 | 0.5149 | 0.3221 | 0.3070 | |
|
| 0.0035 | 10.14 | 700 | 0.5345 | 0.3443 | 0.3266 | |
|
| 0.0027 | 11.59 | 800 | 0.5339 | 0.3344 | 0.3175 | |
|
| 0.0026 | 13.04 | 900 | 0.5435 | 0.3328 | 0.3134 | |
|
| 0.0037 | 14.49 | 1000 | 0.5346 | 0.2714 | 0.2506 | |
|
| 0.0045 | 15.94 | 1100 | 0.5438 | 0.3389 | 0.3220 | |
|
| 0.0028 | 17.39 | 1200 | 0.5588 | 0.2740 | 0.2551 | |
|
| 0.0036 | 18.84 | 1300 | 0.5466 | 0.2702 | 0.2728 | |
|
| 0.0035 | 20.29 | 1400 | 0.5364 | 0.3332 | 0.3119 | |
|
| 0.0056 | 21.74 | 1500 | 0.5608 | 0.2721 | 0.2506 | |
|
| 0.0037 | 23.19 | 1600 | 0.5443 | 0.3027 | 0.2833 | |
|
| 0.0035 | 24.64 | 1700 | 0.5466 | 0.3866 | 0.3631 | |
|
| 0.0024 | 26.09 | 1800 | 0.5628 | 0.3416 | 0.3198 | |
|
| 0.0036 | 27.54 | 1900 | 0.5495 | 0.3122 | 0.2946 | |
|
| 0.0016 | 28.99 | 2000 | 0.5728 | 0.3943 | 0.3664 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0.dev0 |
|
- Pytorch 1.12.1+cu116 |
|
- Datasets 2.4.0 |
|
- Tokenizers 0.12.1 |
|
|
