Spoken language identification for 12 Nigerian languages (DSN 2026)
Submission of team "godzilla" to the DSN 2026 Find the Language I Am Speaking competition.
A standard HubertForSequenceClassification model (loads with AutoModelForAudioClassification, no custom code).
It predicts one of 13 labels: yor ibo hau ego anw efi ibb idu igl nup tiv urh other.
Approach
AfriHuBERT truncated to its first 4 transformer layers with a weighted layer sum and mean pooling, fine-tuned on random 3-6 s crops with speaker- and source-balanced sampling and audio augmentation (synthetic noise, reverberation, telephone band-limiting and companding, speed and equalisation changes). Inference uses the full clip.
Base model
- ajesujoba/AfriHuBERT, a continued pretraining of utter-project/mHuBERT-147 (CC BY-NC-SA 4.0). This model inherits that licence.
Training data
- Competition training and validation data, Data-Science-Nigeria/dsn-2026-lid-train, which combines afrispeech_ipa (CC-BY-4.0), hypa_voices (Apache-2.0) and omnilingual_asr (CC-BY-4.0); see its ATTRIBUTION.md. No other use of those corpora.
- No external data.
Usage
from transformers import AutoFeatureExtractor, AutoModelForAudioClassification
fe = AutoFeatureExtractor.from_pretrained('godzilla1215/dsn2026-lid-d2')
model = AutoModelForAudioClassification.from_pretrained('godzilla1215/dsn2026-lid-d2')
inputs = fe(waveform_16khz_mono, sampling_rate=16000, return_tensors="pt")
label = model.config.id2label[model(**inputs).logits.argmax(-1).item()]
- Downloads last month
- 15