---
language:
- hi
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: openai/whisper-tiny
datasets:
- mozilla-foundation/common_voice_17_0
model-index:
- name: Whisper tiny Hindi
  results: 
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Common Voice 17.0
      type: mozilla-foundation/common_voice_17_0
      config: hi
      split: None
      args: 'config: hi, split: test'
    metrics:
    - name: Wer
      type: wer
      value: 44.76572739187418
      #'eval/wer': 73.09662131172604, 'eval/normalized_wer': 44.76572739187418
---

<!-- 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 tiny Hindi

This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 17.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7189

## 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: 0.001
- train_batch_size: 32
- 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: 50
- num_epochs: 1
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.575         | 0.4484 | 100  | 0.8603          |
| 0.6631        | 0.8969 | 200  | 0.7189          |


### Framework versions

- PEFT 0.11.2.dev0
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.3.dev0
- Tokenizers 0.19.1