---
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-Yfreq_speed_pause
  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-Yfreq_speed_pause

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the aihub old50 adult freq pause changed dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1709
- Cer: 4.6875

## 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    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 0.2988        | 0.1289 | 100  | 0.2504          | 6.3675 |
| 0.1789        | 0.2579 | 200  | 0.2206          | 6.2735 |
| 0.1877        | 0.3868 | 300  | 0.2060          | 5.6508 |
| 0.164         | 0.5158 | 400  | 0.1973          | 5.4394 |
| 0.1333        | 0.6447 | 500  | 0.1936          | 5.2573 |
| 0.1265        | 0.7737 | 600  | 0.1814          | 4.8931 |
| 0.1231        | 0.9026 | 700  | 0.1780          | 4.9518 |
| 0.0691        | 1.0316 | 800  | 0.1750          | 4.7521 |
| 0.0564        | 1.1605 | 900  | 0.1775          | 4.9577 |
| 0.0583        | 1.2895 | 1000 | 0.1747          | 4.7404 |
| 0.057         | 1.4184 | 1100 | 0.1752          | 4.9871 |
| 0.0504        | 1.5474 | 1200 | 0.1724          | 4.6346 |
| 0.052         | 1.6763 | 1300 | 0.1722          | 5.0164 |
| 0.0441        | 1.8053 | 1400 | 0.1713          | 4.6758 |
| 0.0472        | 1.9342 | 1500 | 0.1709          | 4.6875 |


### Framework versions

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