---
language: lg
library_name: transformers
pipeline_tag: automatic-speech-recognition
tags:
- automatic-speech-recognition
- whisper
- non-standard-speech
datasets:
- google/WaxalNLP
metrics:
- wer
---

This is a fine-tuned version of [**`openai/whisper-large-v3`**](https://huggingface.co/openai/whisper-large-v3) for `Luganda` standard speech. It is part of CDLI's effort to make speech technology work for people whose speech is underserved by mainstream ASR systems.

All CDLI models and datasets can be found on [**CDLI's HuggingFace page**](https://huggingface.co/cdli).

## Dataset

The model has been fine-tuned using [`google/WaxalNLP`](https://huggingface.co/datasets/google/WaxalNLP). The `lug_asr` subset of the dataset was used.

## Training

The *train* split was used for training, and the *dev* split for selecting the best checkpoint. 

This Whisper model was fine-tuned and is decoded using the **Swahili** (`sw`) language setting — out of all languages Whisper supports, the one most similar to Luganda.

All model parameters (encoder, decoder, and output projection) were fine-tuned, with SpecAugment enabled.

## Evaluation

This model was evaluated on the **`test`** split of the dataset. Utterances longer than 30 seconds were excluded:
- **Examples evaluated:** 503
- **Speakers:** 194

For decoding we ran Whisper with `language=sw`, `task=transcribe`,
greedy search (`num_beams=1`, `do_sample=False`).



We report two complementary word error rate (WER) metrics, both computed on text
normalized with Whisper's `BasicTextNormalizer`:

- **Standard (corpus-level) WER** — the usual error rate, pooling all reference
  words and edit errors across the entire test set.
- **Per-utterance averaged WER** — WER computed *separately for each utterance*,
  each capped at 1.0, then averaged across utterances.

The per-utterance averaged WER bounds each utterance to
[0, 1] and weights all utterances equally, so it reflects typical performance
without a few catastrophic utterances dominating — but it is not a true error
rate and isn't directly comparable to other published WER, hence we report the standard, corpus-level WER as well.

## Results

### Overall Results


| Model | Standard WER | Per-utterance averaged WER |
| ----- | ------------ | -------------------------- |
| **This model** | 0.13 | 0.13 |