---
language:
- hi
base_model: nurzhanit/whisper-enhanced-ml
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Small Hi - Sanchit Gandhi
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Common Voice 11.0
      type: mozilla-foundation/common_voice_11_0
      config: default
      split: None
      args: 'config: hi, split: test'
    metrics:
    - name: Wer
      type: wer
      value: 0.05063291139240507
---

<!-- 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 [nurzhanit/whisper-enhanced-ml](https://huggingface.co/nurzhanit/whisper-enhanced-ml) on the Common Voice 11.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0002
- Wer: 0.0506

## 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: 50
- training_steps: 1000

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Wer    |
|:-------------:|:-------:|:----:|:---------------:|:------:|
| 0.0339        | 0.8621  | 50   | 0.0211          | 2.5316 |
| 0.0237        | 1.7241  | 100  | 0.0104          | 1.5949 |
| 0.0109        | 2.5862  | 150  | 0.0058          | 0.8354 |
| 0.0046        | 3.4483  | 200  | 0.0029          | 0.4051 |
| 0.0038        | 4.3103  | 250  | 0.0014          | 0.1519 |
| 0.0017        | 5.1724  | 300  | 0.0015          | 0.4051 |
| 0.0019        | 6.0345  | 350  | 0.0006          | 0.2025 |
| 0.0011        | 6.8966  | 400  | 0.0005          | 0.2532 |
| 0.0007        | 7.7586  | 450  | 0.0004          | 0.0506 |
| 0.0002        | 8.6207  | 500  | 0.0004          | 0.0506 |
| 0.0003        | 9.4828  | 550  | 0.0003          | 0.0506 |
| 0.0004        | 10.3448 | 600  | 0.0003          | 0.0506 |
| 0.0001        | 11.2069 | 650  | 0.0002          | 0.0506 |
| 0.0004        | 12.0690 | 700  | 0.0002          | 0.0506 |
| 0.0002        | 12.9310 | 750  | 0.0002          | 0.0506 |
| 0.0004        | 13.7931 | 800  | 0.0002          | 0.0506 |
| 0.0001        | 14.6552 | 850  | 0.0002          | 0.0506 |
| 0.0002        | 15.5172 | 900  | 0.0002          | 0.0506 |
| 0.0003        | 16.3793 | 950  | 0.0002          | 0.0506 |
| 0.0002        | 17.2414 | 1000 | 0.0002          | 0.0506 |


### Framework versions

- Transformers 4.40.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.2
- Tokenizers 0.19.1