---
language:
- vi
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- vivos
metrics:
- wer
model-index:
- name: Whisper Small Hi - Sanchit Gandhi
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: '##'
      type: vivos
      config: vi
      split: None
      args: 'config: vi, split: test'
    metrics:
    - name: Wer
      type: wer
      value: 28.687356069744492
---

<!-- 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 Hi - Sanchit Gandhi

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the ## dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5230
- Wer: 28.6874

## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- training_steps: 200
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.2772        | 0.57  | 100  | 0.5491          | 29.9594 |
| 0.1497        | 1.15  | 200  | 0.5230          | 28.6874 |


### Framework versions

- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2