---
library_name: transformers
language:
- hi
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- aihub_adult_baseline
model-index:
- name: whisper-small-E30
  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-small-E30

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the aihub old adult freq speed pause changed dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1876
- Cer: 4.9871

## 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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 50
- num_epochs: 2
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Cer    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 0.5847        | 0.4301 | 100  | 0.2457          | 5.8271 |
| 0.3748        | 0.8602 | 200  | 0.1978          | 5.4864 |
| 0.148         | 1.2882 | 300  | 0.1925          | 5.0693 |
| 0.1831        | 1.7183 | 400  | 0.1876          | 4.9871 |


### Framework versions

- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0