|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: openai/whisper-small |
|
datasets: |
|
- mozilla-foundation/common_voice_6_1 |
|
model-index: |
|
- name: LoRA-Frisian-10m |
|
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. --> |
|
|
|
# LoRA-Frisian-10m |
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the mozilla-foundation/common_voice_6_1 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.4653 |
|
|
|
## 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: 0.001 |
|
- 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_steps: 50 |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| No log | 1.0 | 15 | 3.9065 | |
|
| 4.5818 | 2.0 | 30 | 2.4690 | |
|
| 4.5818 | 3.0 | 45 | 2.1054 | |
|
| 1.9044 | 4.0 | 60 | 1.5722 | |
|
| 0.6082 | 5.0 | 75 | 1.4697 | |
|
| 0.6082 | 6.0 | 90 | 1.4806 | |
|
| 0.1604 | 7.0 | 105 | 1.4372 | |
|
| 0.1604 | 8.0 | 120 | 1.5410 | |
|
| 0.0994 | 9.0 | 135 | 1.4781 | |
|
| 0.1083 | 10.0 | 150 | 1.4653 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.40.1 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |