|
--- |
|
license: apache-2.0 |
|
base_model: openai/whisper-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: whisper_finetuned_ver2 |
|
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_finetuned_ver2 |
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0048 |
|
- Cer: 0.5262 |
|
- Wer: 0.4840 |
|
|
|
## 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: 32 |
|
- 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: 5000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer | |
|
|:-------------:|:------:|:----:|:---------------:|:------:|:------:| |
|
| 0.0 | 35.71 | 1000 | 0.0047 | 0.5496 | 0.5227 | |
|
| 0.0001 | 71.43 | 2000 | 0.0048 | 0.5262 | 0.4840 | |
|
| 0.0 | 107.14 | 3000 | 0.0051 | 0.5964 | 0.5615 | |
|
| 0.0 | 142.86 | 4000 | 0.0053 | 0.6080 | 0.5808 | |
|
| 0.0 | 178.57 | 5000 | 0.0054 | 0.6080 | 0.5808 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.0.dev0 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
