|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
base_model: openai/whisper-base.en |
|
tags: |
|
- hf-asr-leaderboard |
|
- 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 [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on the ADLINK dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0003 |
|
- Wer: 1.2422 |
|
|
|
## 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: 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: 500 |
|
- training_steps: 1000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:------:|:----:|:---------------:|:-------:| |
|
| 1.5447 | 33.33 | 100 | 1.2099 | 11.4907 | |
|
| 0.4211 | 66.67 | 200 | 0.3868 | 1.5528 | |
|
| 0.0987 | 100.0 | 300 | 0.0761 | 1.8634 | |
|
| 0.006 | 133.33 | 400 | 0.0040 | 1.2422 | |
|
| 0.0011 | 166.67 | 500 | 0.0010 | 1.2422 | |
|
| 0.0006 | 200.0 | 600 | 0.0006 | 1.2422 | |
|
| 0.0004 | 233.33 | 700 | 0.0004 | 1.2422 | |
|
| 0.0003 | 266.67 | 800 | 0.0003 | 1.2422 | |
|
| 0.0003 | 300.0 | 900 | 0.0003 | 1.2422 | |
|
| 0.0003 | 333.33 | 1000 | 0.0003 | 1.2422 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.0.dev0 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|
