|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: openai/whisper-medium |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: whisper-medium-studio-records_test |
|
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-studio-records_test |
|
|
|
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0333 |
|
- Wer: 15.6507 |
|
|
|
## 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: 1000 |
|
- training_steps: 6000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:------:|:----:|:---------------:|:-------:| |
|
| 0.0568 | 0.4110 | 1000 | 0.0894 | 43.3939 | |
|
| 0.0362 | 0.8220 | 2000 | 0.0589 | 29.9079 | |
|
| 0.0149 | 1.2330 | 3000 | 0.0463 | 22.6922 | |
|
| 0.0117 | 1.6441 | 4000 | 0.0375 | 19.2088 | |
|
| 0.0039 | 2.0551 | 5000 | 0.0355 | 16.1483 | |
|
| 0.0032 | 2.4661 | 6000 | 0.0333 | 15.6507 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
