---
library_name: transformers
language:
- en
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- data_tcd_india
metrics:
- wer
model-index:
- name: Whisper Small TCD
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: data_tcd
      type: data_tcd_india
      args: 'config: english, split: test'
    metrics:
    - name: Wer
      type: wer
      value: 4.473391433339515
---

<!-- 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 TCD

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co./openai/whisper-small) on the data_tcd dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1792
- Wer: 4.4734

## 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: 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: 500
- training_steps: 3000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Wer    |
|:-------------:|:-------:|:----:|:---------------:|:------:|
| 0.0144        | 3.4364  | 1000 | 0.1505          | 4.5337 |
| 0.0012        | 6.8729  | 2000 | 0.1699          | 4.4641 |
| 0.0004        | 10.3093 | 3000 | 0.1792          | 4.4734 |


### Framework versions

- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0