whisper-base.en / README.md
crossdelenna's picture
update model card README.md
49535a3
|
raw
history blame
1.59 kB
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-base.en
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.en
This model is a fine-tuned version of [crossdelenna/whisper-base.en](https://huggingface.co/crossdelenna/whisper-base.en) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0002
- Wer: 0.5704
## 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: 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: 500
- training_steps: 2000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.0078 | 1.62 | 500 | 0.0067 | 1.1008 |
| 0.0018 | 3.25 | 1000 | 0.0006 | 0.6404 |
| 0.0002 | 4.87 | 1500 | 0.0002 | 0.5604 |
| 0.0002 | 6.49 | 2000 | 0.0002 | 0.5704 |
### Framework versions
- Transformers 4.28.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2