---
language:
- en
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- deepsync-ai/translation-hi-en-whisper
model-index:
- name: Hindi to English Translation
  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. -->

# Hindi to English Translation

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Translation Data dataset.
It achieves the following results on the evaluation set:
- eval_loss: 1.4841
- eval_wer: 70.4717
- eval_runtime: 468.5856
- eval_samples_per_second: 2.313
- eval_steps_per_second: 0.29
- epoch: 1.6393
- step: 1000

## 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP

### Framework versions

- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1