---
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-Ypause_speed
  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-Ypause_speed

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: 0.3047
- Cer: 7.9828

## 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    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 0.2579        | 0.1290 | 100  | 0.2921          | 8.2472 |
| 0.146         | 0.2581 | 200  | 0.2830          | 7.6833 |
| 0.1177        | 0.3871 | 300  | 0.2817          | 7.6245 |
| 0.1107        | 0.5161 | 400  | 0.2889          | 8.1708 |
| 0.082         | 0.6452 | 500  | 0.2890          | 7.9359 |
| 0.0908        | 0.7742 | 600  | 0.2859          | 7.6833 |
| 0.0866        | 0.9032 | 700  | 0.2916          | 7.8889 |
| 0.0331        | 1.0323 | 800  | 0.3022          | 8.0768 |
| 0.0275        | 1.1613 | 900  | 0.2975          | 7.8184 |
| 0.0297        | 1.2903 | 1000 | 0.2896          | 7.5129 |
| 0.0311        | 1.4194 | 1100 | 0.3048          | 8.0063 |
| 0.0221        | 1.5484 | 1200 | 0.3129          | 8.1238 |
| 0.0243        | 1.6774 | 1300 | 0.3015          | 7.8419 |
| 0.025         | 1.8065 | 1400 | 0.3026          | 7.9006 |
| 0.0239        | 1.9355 | 1500 | 0.3047          | 7.9828 |


### Framework versions

- Transformers 4.47.0.dev0
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3