|
|
---
|
|
|
library_name: peft
|
|
|
tags:
|
|
|
- generated_from_trainer
|
|
|
base_model: Wsassi/whisper-small-minds14
|
|
|
metrics:
|
|
|
- wer
|
|
|
model-index:
|
|
|
- name: whisper-small-minds14
|
|
|
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-small-minds14 |
|
|
|
|
|
This model is a fine-tuned version of [Wsassi/whisper-small-minds14](https://huggingface.co/Wsassi/whisper-small-minds14) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.2677 |
|
|
- Wer: 6.4516 |
|
|
|
|
|
## 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: 4 |
|
|
- eval_batch_size: 4 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- training_steps: 200 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
|
| 2.2898 | 12.5 | 25 | 2.8612 | 3.2258 | |
|
|
| 2.0737 | 25.0 | 50 | 2.1099 | 3.2258 | |
|
|
| 1.4161 | 37.5 | 75 | 1.6899 | 3.2258 | |
|
|
| 1.2353 | 50.0 | 100 | 1.4505 | 3.2258 | |
|
|
| 1.1164 | 62.5 | 125 | 1.3412 | 3.2258 | |
|
|
| 1.1138 | 75.0 | 150 | 1.2952 | 6.4516 | |
|
|
| 0.9938 | 87.5 | 175 | 1.2741 | 6.4516 | |
|
|
| 1.0179 | 100.0 | 200 | 1.2677 | 6.4516 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.11.1 |
|
|
- Transformers 4.37.2 |
|
|
- Pytorch 2.2.0+cu118 |
|
|
- Datasets 2.19.2 |
|
|
- Tokenizers 0.15.1 |
