---
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-Yspeed_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-Yspeed_pause

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the aihub adult speed pause changed dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2868
- Cer: 9.4102

## 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     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.4718        | 0.1289 | 100  | 0.3154          | 7.5658  |
| 0.29          | 0.2579 | 200  | 0.2799          | 7.9065  |
| 0.2301        | 0.3868 | 300  | 0.2832          | 8.2178  |
| 0.2239        | 0.5158 | 400  | 0.2696          | 8.0005  |
| 0.2012        | 0.6447 | 500  | 0.2770          | 9.6628  |
| 0.1721        | 0.7737 | 600  | 0.2841          | 7.8301  |
| 0.1762        | 0.9026 | 700  | 0.2802          | 7.7949  |
| 0.0874        | 1.0316 | 800  | 0.2789          | 7.5952  |
| 0.0614        | 1.1605 | 900  | 0.2753          | 8.0063  |
| 0.0704        | 1.2895 | 1000 | 0.2806          | 11.4897 |
| 0.0656        | 1.4184 | 1100 | 0.2870          | 9.8332  |
| 0.0752        | 1.5474 | 1200 | 0.2816          | 10.0564 |
| 0.0603        | 1.6763 | 1300 | 0.2843          | 8.3000  |
| 0.0649        | 1.8053 | 1400 | 0.2858          | 8.6525  |
| 0.0626        | 1.9342 | 1500 | 0.2868          | 9.4102  |


### Framework versions

- Transformers 4.46.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0