|
---
|
|
library_name: peft
|
|
license: apache-2.0
|
|
base_model: openai/whisper-medium
|
|
tags:
|
|
- generated_from_trainer
|
|
metrics:
|
|
- wer
|
|
model-index:
|
|
- name: whisper-medium-cdsd1h-lora
|
|
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-medium-cdsd1h-lora |
|
|
|
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8196 |
|
- Wer: 68.7556 |
|
- Cer: 42.4589 |
|
|
|
## 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: 16 |
|
- 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: 100 |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:| |
|
| 0.8709 | 1.0 | 559 | 0.9190 | 78.1558 | 48.5899 | |
|
| 0.6026 | 2.0 | 1118 | 0.8174 | 73.1871 | 45.7778 | |
|
| 0.3343 | 3.0 | 1677 | 0.7864 | 70.3223 | 41.8295 | |
|
| 0.1663 | 4.0 | 2236 | 0.7846 | 68.8004 | 44.3636 | |
|
| 0.0664 | 5.0 | 2795 | 0.8196 | 68.7556 | 42.4589 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.13.2 |
|
- Transformers 4.44.2 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
