---
license: apache-2.0
language:
- ne
metrics:
- wer
base_model:
- openai/whisper-small
tags:
- automatic-speech-recognition
- whisper
- openslr
- generated_from_trainer
- speech
model-index:
- name: Whisper Small Nepali (OpenSLR)
  results:
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      name: OpenSLR 54 (Nepali Speech Corpus)
      type: openslr
    metrics:
    - type: wer
      value: 26.69
      name: Wer
---

# Whisper Small Fine-tuned on Nepali (OpenSLR 54)

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the **OpenSLR 54 (Nepali Speech Corpus)** dataset. It achieves state-of-the-art results for an open-source small model on this benchmark, trained on a massive 154-hour dataset.

## Model Details

### Model Description

- **Model architecture:** Whisper Small (244M Parameters)
- **Language:** Nepali (ne)
- **Task:** Automatic Speech Recognition (Transcription)
- **Dataset:** OpenSLR 54 (~157,000 utterances)
- **Fine-tuning Hardware:** NVIDIA A100 80GB

## Usage

```python
from transformers import pipeline

transcriber = pipeline("automatic-speech-recognition", model="fnawaraj/whisper-small-nepali-openslr")

# Transcribe an audio file
transcription = transcriber("path_to_nepali_audio.mp3")

print(transcription["text"])
```

## Training Data

The model was trained on the OpenSLR 54 (Nepali Speech Corpus).

    Total Audio Duration: ~154 Hours

    Total Utterances: 157,905

    Sampling Rate: 16kHz

### Training Procedure
#### Training Hyperparameters

The following hyperparameters were used during training:

    Learning Rate: 1e-05

    Train Batch Size: 8

    Eval Batch Size: 8

    Gradient Accumulation Steps: 4 (Effective Batch Size: 32)

    Optimizer: AdamW

    LR Scheduler: Linear decay with warmup (500 steps)

    Training Steps: 10,000

    Mixed Precision: FP16

## Evaluation Results

The model was evaluated on the unseen test split of the OpenSLR dataset (1,580 samples).
Metric	Score
Word Error Rate (WER)	26.69%
Validation Loss	0.210
## Limitations

    The model performs best on read speech (high quality).

    It may struggle with extremely fast conversational speech or heavy background noise compared to models trained on diverse noise datasets.

    Some phonetic spelling variations (e.g., short vs long vowels) may occur as they sound identical in spoken Nepali.


This research was supported by the High Performance Computing (HPC) facility at Tribhuvan University, Nepal. We acknowledge the Supercomputer Centre for providing the computational resources required for this wor