|
---
|
|
library_name: peft
|
|
license: apache-2.0
|
|
base_model: openai/whisper-base
|
|
tags:
|
|
- generated_from_trainer
|
|
metrics:
|
|
- wer
|
|
model-index:
|
|
- name: whisper-base-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-base-cdsd1h-lora |
|
|
|
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: 1.1538 |
|
- Wer: 80.9311 |
|
- Cer: 54.8108 |
|
|
|
## 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: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:| |
|
| 1.26 | 1.0 | 559 | 1.2699 | 88.5407 | 75.2064 | |
|
| 0.9831 | 2.0 | 1118 | 1.1855 | 86.8845 | 68.5931 | |
|
| 0.8122 | 3.0 | 1677 | 1.1086 | 82.5873 | 66.3942 | |
|
| 0.6565 | 4.0 | 2236 | 1.0974 | 83.6616 | 71.2172 | |
|
| 0.5474 | 5.0 | 2795 | 1.0791 | 82.5425 | 57.2223 | |
|
| 0.4118 | 6.0 | 3354 | 1.0899 | 81.1996 | 57.5084 | |
|
| 0.2976 | 7.0 | 3913 | 1.1049 | 81.1996 | 55.4729 | |
|
| 0.1923 | 8.0 | 4472 | 1.1130 | 80.8863 | 57.0343 | |
|
| 0.1222 | 9.0 | 5031 | 1.1395 | 80.7968 | 55.4974 | |
|
| 0.073 | 10.0 | 5590 | 1.1538 | 80.9311 | 54.8108 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.13.2 |
|
- Transformers 4.44.2 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
