|
--- |
|
license: apache-2.0 |
|
base_model: openai/whisper-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- recall |
|
- precision |
|
model-index: |
|
- name: whisper-base-finetuned-common_voice |
|
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-base-finetuned-common_voice |
|
|
|
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0319 |
|
- Accuracy: 0.9925 |
|
- F1: 0.9925 |
|
- Recall: 0.9925 |
|
- Precision: 0.9927 |
|
- Mcc: 0.9907 |
|
- Auc: 0.9999 |
|
|
|
## 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: 8 |
|
- 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_ratio: 0.1 |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision | Mcc | Auc | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|:------:|:------:| |
|
| 0.1765 | 1.0 | 200 | 0.1455 | 0.9775 | 0.9775 | 0.9775 | 0.9776 | 0.9719 | 0.9996 | |
|
| 0.0067 | 2.0 | 400 | 0.0734 | 0.98 | 0.9800 | 0.9800 | 0.9804 | 0.9751 | 0.9996 | |
|
| 0.0218 | 3.0 | 600 | 0.0719 | 0.9875 | 0.9875 | 0.9875 | 0.9879 | 0.9845 | 0.9999 | |
|
| 0.002 | 4.0 | 800 | 0.1055 | 0.975 | 0.9752 | 0.975 | 0.9762 | 0.9690 | 0.9997 | |
|
| 0.0014 | 5.0 | 1000 | 0.0312 | 0.995 | 0.9950 | 0.9950 | 0.9951 | 0.9938 | 0.9999 | |
|
| 0.0011 | 6.0 | 1200 | 0.0305 | 0.995 | 0.9950 | 0.9950 | 0.9951 | 0.9938 | 0.9999 | |
|
| 0.0009 | 7.0 | 1400 | 0.0310 | 0.995 | 0.9950 | 0.9950 | 0.9951 | 0.9938 | 0.9999 | |
|
| 0.0008 | 8.0 | 1600 | 0.0315 | 0.9925 | 0.9925 | 0.9925 | 0.9927 | 0.9907 | 0.9999 | |
|
| 0.0008 | 9.0 | 1800 | 0.0318 | 0.9925 | 0.9925 | 0.9925 | 0.9927 | 0.9907 | 0.9999 | |
|
| 0.0007 | 10.0 | 2000 | 0.0319 | 0.9925 | 0.9925 | 0.9925 | 0.9927 | 0.9907 | 0.9999 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
