---
license: apache-2.0
base_model: stepfun-ai/Step-Audio-2-mini
library_name: peft
tags:
- audio
- speech-translation
- speech-to-speech
- luganda
- english
- stepaudio2
model-index:
- name: Step-Audio 2 Mini Luganda-to-English S2ST LoRA
  results:
  - task:
      type: speech-translation
      name: Luganda-to-English speech translation
    dataset:
      type: yigagilbert/luganda-english-cleaned-v1-split
      name: Luganda-English Cleaned v1 Split
      split: validation
    metrics:
    - type: bleu
      name: BLEU
      value: 32.530
    - type: chrf
      name: chrF
      value: 54.535
    - type: wer
      name: WER on generated English text
      value: 0.574
    - type: comet
      name: COMET
      value: 0.717
    - type: blaser_2_0_ref
      name: BLASER 2.0 ref
      value: 3.762
    - type: blaser_2_0_qe
      name: BLASER 2.0 QE
      value: 3.723
---

# Step-Audio 2 Mini Luganda-to-English S2ST LoRA

This repository contains a LoRA adapter for `stepfun-ai/Step-Audio-2-mini` trained for
Luganda speech input to English speech output. The adapter requires the base model and
Step-Audio 2 `token2wav` assets for waveform synthesis.

Adapter repository: `yigagilbert/stepaudio2-mini-luganda-english-s2st-lora`

## Intended use

Research and development for Luganda-to-English speech translation. Validate with native
speakers before production use.

## Training data

Configured for `yigagilbert/luganda-english-cleaned-v1-split` with columns:
`audio_lug`, `audio_eng`, `text_lug`, `text_eng`, `id`, `src_dur_s`, `tgt_dur_s`,
`dur_ratio`, `src_speech_ratio`, `tgt_speech_ratio`.

## Evaluation

The table below summarizes the held-out validation evaluation used during development.
All text metrics were computed on 200 validation examples. Speech metrics were computed
on the aligned 197-example subset for which generated audio existed.

The merged full-model repository contains the same adapted weights as this adapter after
LoRA merge, so it is expected to match these results aside from normal deterministic or
runtime differences. Re-run evaluation directly on the merged repository before a strict
release if exact reproducibility is required.

### Text and Semantic Metrics

| System | Loading Form | Count | BLEU higher | chrF higher | WER lower | COMET higher | BLASER ref higher | BLASER QE higher |
|---|---|---:|---:|---:|---:|---:|---:|---:|
| Base Step-Audio-2-mini | Base only | 200 | 0.012 | 5.152 | 10.702 | 0.386 | 1.713 | 2.164 |
| Fine-tuned Step-Audio | Base + this LoRA adapter | 200 | 32.530 | 54.535 | 0.574 | 0.717 | 3.762 | 3.723 |
| Full merged fine-tuned model | Same adapted weights, merged | 200 | 32.530* | 54.535* | 0.574* | 0.717* | 3.762* | 3.723* |
| Cascade baseline | ASR + MT + TTS | 200 | 36.778 | 57.971 | 0.521 | 0.737 | 3.839 | 3.776 |

`*` The merged full-model row reflects the adapter evaluation because the merged
repository is produced by folding this LoRA adapter into the same base model.

### Speech Metrics

| System | Count | chrF higher | SpeechBERT P higher | SpeechBERT R higher | SpeechBERT F1 higher | MCD lower |
|---|---:|---:|---:|---:|---:|---:|
| Fine-tuned Step-Audio | 197 | 54.582 | 0.644 | 0.648 | 0.645 | 629.718 |
| Full merged fine-tuned model | 197 | 54.582* | 0.644* | 0.648* | 0.645* | 629.718* |
| Cascade baseline | 197 | 57.893 | 0.603 | 0.622 | 0.612 | 613.212 |

The unfine-tuned base model emitted no valid speech-token sequences in this 200-sample
run, so SpeechBERTScore and MCD were not computed for it.

### Interpretation

The LoRA adapter changes the base model from an unusable zero-shot system into a
functioning Luganda-to-English speech translation model. The cascade remains stronger
on text and semantic metrics, while the fine-tuned Step-Audio system is operationally
simpler and scored higher on the WavLM-based SpeechBERTScore F1 proxy.

## License

Adapter code and metadata are Apache-2.0. Check the dataset license separately before
redistribution.