---
language:
- bn
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_13_0
metrics:
- wer
model-index:
- name: Whisper in Bangla
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Common Voice 13
      type: mozilla-foundation/common_voice_13_0
      config: bn
      split: test
      args: bn
    metrics:
    - name: Wer
      type: wer
      value: 36.383706024782796
---

<!-- 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 in Bangla

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1242
- Wer: 36.3837

## 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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 1000

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.0544        | 0.27  | 500  | 0.1283          | 37.4448 |
| 0.0526        | 0.53  | 1000 | 0.1242          | 36.3837 |


### Framework versions

- Transformers 4.31.0
- Pytorch 2.0.0
- Datasets 2.14.2
- Tokenizers 0.13.3