w2v-bert-2.0-lang-id-lug-sna-lin

w2v-bert-2.0-lang-id-lug-sna-lin

A spoken language identification (LID) model that classifies short audio clips into one of three languages — Luganda, Shona, or Lingala — fine-tuned from facebook/w2v-bert-2.0 with a sequence classification head, trained on the WAXAL corpus only.

Model description

facebook/w2v-bert-2.0 — a large-scale, multilingual self-supervised speech encoder pretrained with a BERT-style masked prediction objective — is used as the backbone, with a from-scratch audio classification head fine-tuned to predict which of the three languages a given audio clip is spoken in. Unlike the companion ASR models in this collection, this model does not transcribe speech — it only outputs a language label.

Training data

Only WAXAL data was used — no additional community datasets were pooled in.

Training procedure

• Base model: facebook/w2v-bert-2.0
• Architecture: Wav2Vec2BertForSequenceClassification (audio classification head over the pretrained encoder), 3 output classes (Luganda, Shona, Lingala)
• Sample rate: 16 kHz mono
• Hardware: single RTX PRO 6000

Evaluation results

This model achieved perfect accuracy (100%) on both the validation and test splits, correctly classifying every clip across all three languages.

Note: Perfect accuracy on a 3-way language ID task like this is plausible — Luganda, Shona, and Lingala are phonologically quite distinct from each other, which makes the classification task much easier than, say, distinguishing closely related dialects. As always, treat in-domain WAXAL numbers as an upper bound rather than a guarantee of real-world performance on out-of-domain audio.

How to use

import torch
import librosa
from transformers import Wav2Vec2BertForSequenceClassification, Wav2Vec2BertProcessor

MODEL_ID = "keystats/w2v-bert-2.0-lang-id-lug-sna-lin"
DEVICE = "cuda" if torch.cuda.is_available() else "cpu"

processor = Wav2Vec2BertProcessor.from_pretrained(MODEL_ID)
model = Wav2Vec2BertForSequenceClassification.from_pretrained(MODEL_ID).to(DEVICE).eval()

audio_array, sr = librosa.load("path/to/audio.wav", sr=16000, mono=True)
inputs = processor(audio_array, sampling_rate=16000, return_tensors="pt")
with torch.no_grad():
    logits = model(input_features=inputs.input_features.to(DEVICE)).logits

predicted_id = torch.argmax(logits, dim=-1).item()
predicted_label = model.config.id2label[predicted_id]

print(predicted_label)  # "luganda", "shona", or "lingala"

Intended uses & limitations

• Intended for identifying which of Luganda, Shona, or Lingala is being spoken in a given audio clip — useful as a pre-processing step to route audio to the correct language-specific ASR model (e.g. the Luganda -main-best checkpoints in this collection).
• This is a closed-set 3-way classifier: it will always output one of the three trained languages, even for audio in a different language or non-speech audio. It has no "none of the above" / out-of-domain detection.
• Trained and evaluated only on WAXAL data — perfect validation/test accuracy reflects in-domain WAXAL audio conditions and may not carry over as-is to audio from very different recording conditions, speakers, or dialectal variation.
• Not a general-purpose language ID model — it only distinguishes between these three specific languages, not the full range of African languages or languages generally.

Citation

If you use this model, please cite the training/fine-tuning work and the underlying dataset:

@misc{keystats_wav2vec2bert_langid_lug_sna_lin,
  title={w2v-bert-2.0-lang-id-lug-sna-lin: A Luganda/Shona/Lingala spoken language identification model fine-tuned from facebook/w2v-bert-2.0},
  author={keystats},
  year={2026},
  howpublished={\url{https://huggingface.co/keystats/w2v-bert-2.0-lang-id-lug-sna-lin}}
}

@misc{waxal,
  title={WAXAL: A Multilingual African Speech Dataset},
  author={Google},
  howpublished={\url{https://huggingface.co/datasets/google/WaxalNLP}}
}

@inproceedings{w2vbert2,
  title={Seamless: Multilingual Expressive and Streaming Speech Translation},
  author={Seamless Communication and others},
  year={2023},
  howpublished={\url{https://huggingface.co/facebook/w2v-bert-2.0}}
}