Ubuzima AI
A LoRA adapter over badrex/w2v-bert-2.0-kinyarwanda-asr, fine-tuned for a Kinyarwanda voice health assistant. Part of the UBUZIMA AI capstone project at the African Leadership University, Kigali.
Source du modèle
- Type
- LoRA
- Taille du fichier
- 12,0 MB
- Modèle de base
- badrex/w2v-bert-2.0-kinyarwanda-asr
- Version
- vadapter_model
- Mis à jour
- 26 oct. 2026
- Téléchargements
- 5
- Source
- Hugging Face
Description de la source
UBUZIMA AI — Kinyarwanda ASR LoRA adapter
A LoRA adapter over badrex/w2v-bert-2.0-kinyarwanda-asr, fine-tuned for a Kinyarwanda voice health assistant. Part of the UBUZIMA AI capstone project at the African Leadership University, Kigali.
Model details
- Developed by: Ganza Didier (African Leadership University)
- Model type: LoRA adapter for Wav2Vec2-BERT 2.0 CTC speech recognition
- Language: Kinyarwanda (rw)
- License: Apache 2.0
- Fine-tuned from: badrex/w2v-bert-2.0-kinyarwanda-asr
Adapter configuration
r = 32, alpha = 64, dropout 0.05, target modules linear_q and linear_v.
3,145,728 trainable parameters (0.54% of the 583.6M base). Feature extractor and
feature projection frozen.
Training
Fine-tuned in two sequential stages on pooled Afrivoice (health-domain) and Common Voice (general-domain) Kinyarwanda speech:
- Stage 1: 100 hours at a 1:1 Afrivoice:Common Voice ratio.
- Stage 2: warm-started from Stage 1, 500 hours at a 1:4 ratio. This adapter is the Stage 2 result.
Training regime: fp16 mixed precision on an NVIDIA T4 (Google Colab).
Evaluation
| Test set | n clips | WER | 95% CI | CER |
|---|---|---|---|---|
| Afrivoice (in-domain, health) | 1,560 | 6.76% | [6.44, 7.11] | 1.39% |
| Common Voice (cross-domain, general) | 16,205 | 31.29% | [30.86, 31.72] | 8.99% |
WER = word error rate, CER = character error rate. 95% confidence intervals from 500-resample bootstrapping.
Contamination note. The base badrex checkpoint was pretrained on Kinyarwanda audio that included portions of the Digital Umuganda health corpus from which the Afrivoice subset is drawn. The in-domain figure therefore reflects both this adaptation and residual pretraining familiarity; the Common Voice figure is the cleaner cross-domain measure of what the adapter added.
How to use
from transformers import Wav2Vec2BertForCTC, AutoProcessor
from peft import PeftModel
base = "badrex/w2v-bert-2.0-kinyarwanda-asr"
model = Wav2Vec2BertForCTC.from_pretrained(base)
model = PeftModel.from_pretrained(model, "dganza/Ubuzima_AI")
model = model.merge_and_unload() # fold LoRA in for faster inference
processor = AutoProcessor.from_pretrained("dganza/Ubuzima_AI")
Intended use and limitations
Research prototype for Kinyarwanda health-information delivery. Not a medical device; does not diagnose. Dialect coverage is limited to the standard Kinyarwanda represented in the training corpora. Cross-domain performance (Common Voice, 31% WER) is substantially weaker than in-domain (Afrivoice, 7% WER), so out-of-domain use should expect that gap.
Citation
Ganza, D. (2026). UBUZIMA AI: A Kinyarwanda voice health assistant [Capstone project]. African Leadership University. Supervisor: Emmanuel Adjei.
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
Sources
1 source
Sources
1 sourceVérifié 26 oct.
Artefacts du modèle
1 artefact
Artefacts du modèle
1 artefactadapter_model.safetensors
safetensors · 12,0 MB · SHA-256 527b776b9340…29b4 · Hugging Face
Download fileExtraits de sources
3 extraits
Extraits de sources
3 extraits--- base_model: badrex/w2v-bert-2.0-kinyarwanda-asr library_name: peft license: apache-2.0 language: - rw tags: - automatic-speech-recognition - kinyarwanda - lora - health pipeline_tag: automatic-speech-recognition --- # UBUZIMA AI — Kinyarwanda ASR LoRA adapter A LoRA adapter over [badrex/w2v-bert-2.0-kinyarwanda-asr](https://huggingface.co/badrex/w2v-bert-2.0-kinyarwanda-asr), fine-tuned for a Kinyarwanda voice health assistant. Part of the UBUZIMA AI capstone project at the African Leadership University, Kigali. ## Model details - **Developed by:** Ganza Didier (African Leadership University) - **Model type:** LoRA adapter for Wav2Vec2-BERT 2.0 CTC speech recognition - **Language:** Kinyarwanda (rw) - **License:** Apache 2.0 - **Fine-tuned from:** badrex/w2v-bert-2.0-kinyarwanda-asr ### Adapter configuration r = 32, alpha = 64, dropout 0.05, target modules `linear_q` and `linear_v`. 3,145,728 trainable parameters (0.54% of the 583.6M base). Feature extractor and feature projection frozen. ## Training Fine-tuned in two sequential stages on pooled Afrivoice (health-domain) and Common Voice (general-domain) Kinyarwanda speech: - **Stage 1:** 100 hours at a 1:1 Afrivoice:Common Voice ratio. - **Stage 2:** warm-started from Stage 1, 500 hours at a 1:4 ratio. This adapter is the Stage 2 result. Training regime: fp16 mixed precision on an NVIDIA T4 (Google Colab). ## Evaluation | Test set | n clips | WER | 95% CI | CER | |---|---|---|---|---| | Afrivoice (in-domain, health) | 1,560 | 6.76% | [6.44, 7.11] | 1.39% | | Common Voice (cross-domain, general) | 16,205 | 31.29% | [30.86, 31.72] | 8.99% | WER = word error rate, CER = character error rate. 95% confidence intervals from 500-resample bootstrapping. **Contamination note.** The base badrex checkpoint was pretrained on Kinyarwanda audio that included portions of the Digital Umuganda health corpus from which the Afrivoice subset is drawn. The in-domain figure therefore reflects both this adaptation and residual pretraining familiarity; the Common Voice figure is the cleaner cross-domain measure of what the adapter added. ## How to use ```python from transformers import Wav2Vec2BertForCTC, AutoProcessor from peft import PeftModel base = "badrex/w2v-bert-2.0-kinyarwanda-asr" model = Wav2Vec2BertForCTC.from_pretrained(base) model = PeftModel.from_pretrained(model, "dganza/Ubuzima_AI") model =...
Source context: 36 downloads · 0 likes · Pipeline automatic-speech-recognition · Library peft · Repo dganza/Ubuzima_AI
Source context: 5 downloads · 0 likes · Pipeline automatic-speech-recognition · Library peft · Repo dganza/Ubuzima_AI
