---
library_name: transformers
language:
- pmx
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- iitd-duk/paula
metrics:
- wer
model-index:
- name: Whisper-Small-paula
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Paula
      type: iitd-duk/paula
    metrics:
    - name: Wer
      type: wer
      value: 102.84463894967178
---

<!-- 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-Small-paula

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co./openai/whisper-small) on the Paula dataset.
It achieves the following results on the evaluation set:
- Loss: 3.1674
- Wer: 102.8446

## 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: 12
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer      |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.3851        | 10.0  | 200  | 2.6828          | 101.7505 |
| 0.0097        | 20.0  | 400  | 2.9628          | 101.5317 |
| 0.002         | 30.0  | 600  | 3.1073          | 100.2188 |
| 0.001         | 40.0  | 800  | 3.1528          | 101.9694 |
| 0.0008        | 50.0  | 1000 | 3.1674          | 102.8446 |


### Framework versions

- Transformers 4.46.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1