NaijaVox-2.0

<p align="center"> <img src="https://huggingface.co/Axiveri/NaijaVox-2.0/resolve/main/naijavox_v2_banner.png" width="100%"/> </p> <p align="center"> <img src="https://img.shields.io/badge/Model-NaijaVox--2.0-2ea44f?style=flat-square"/> <img src="https://img.shields.io/badge/License-Apache%202.0-2196F3?style=flat-square"/> <img src="https://img.shields.io/badge/Base-Whisper--Large--v3-8B5CF6?style=flat-square"/> <img src="https://img.shields.io/badge/Version-2.0-FF9800?style=flat-square"/> </p> <p align="center"> <img src="https://img.shields.io/badge/Languages-Yoruba%20%7C%20Hausa%20%7C%20Igbo%20%7C%20Pidgin%20%7C%20Naija%20English-FF6B35?style=flat-square"/> </p> <p align="center"> <img src="https://img.shields.io/badge/Built%20by-Axiveri-e11d48?style=flat-square"/> <img src="https://img.shields.io/badge/GPU-Tesla%20T4%20x2-64748b?style=flat-square"/> </p> <div align="center"> </div>

---

Nigeria's Voice in AI. Now Sharper.

NaijaVox-2.0 is the second generation of Axiveri's open-weight automatic speech recognition model for Nigerian languages — Yoruba (with full diacritics), Hausa, Igbo, Nigerian Pidgin, and Nigerian-accented English. Built on OpenAI Whisper-large-v3 with PEFT LoRA fine-tuning, NaijaVox-2.0 delivers significant accuracy gains over V1 through a larger and more diverse training corpus (25,866 samples across 7 datasets), deeper LoRA adaptation (r=64 targeting attention and feed-forward layers), SpecAugment, and realistic noise augmentation for real-world robustness.

"Every Nigerian deserves to be heard and understood by AI — in their own language, with their own voice."

← NaijaVox-V1 — the original model

---

📈 V1 → V2 Improvement

Evaluated on identical test sets with identical methodology (50 samples/language, strict WER, no normalization):

Igbo sees the largest jump (+27.2% relative) — driven by WaxalNLP Igbo TTS data and Nigerian Common Voice Igbo samples, combined with SpecAugment frequency masking.

---

🗣️ Languages Supported

Note: <\|ig\|> and <\|pcm\|> are custom language tokens added to the Whisper vocabulary. The extended tokenizer is included in this repository.

---

🚀 Quick Start

from transformers import pipeline

pipe = pipeline(
    "automatic-speech-recognition",
    model="Axiveri/NaijaVox-2.0",
    device=0  # use GPU, or remove for CPU
)

result = pipe("your_audio.wav")
print(result["text"])

Specifying Language

from transformers import (
    WhisperForConditionalGeneration, WhisperFeatureExtractor,
    WhisperProcessor, PreTrainedTokenizerFast,
)
from huggingface_hub import hf_hub_download
import torch

MODEL_ID = "Axiveri/NaijaVox-2.0"

model = WhisperForConditionalGeneration.from_pretrained(MODEL_ID)

# Standard load first; this model's custom <|pcm|> / <|ig|> tokens don't
# always come through cleanly this way, so fall back to manually rebuilding
# the tokenizer from tokenizer.json if they're missing.
try:
    processor = WhisperProcessor.from_pretrained(MODEL_ID)
    vocab = processor.tokenizer.get_vocab()
    assert "<|pcm|>" in vocab and "<|ig|>" in vocab
except Exception:
    fe = WhisperFeatureExtractor.from_pretrained(MODEL_ID)
    tok_file = hf_hub_download(repo_id=MODEL_ID, filename="tokenizer.json")
    tokenizer = PreTrainedTokenizerFast(tokenizer_file=tok_file)
    tokenizer.add_special_tokens({
        "additional_special_tokens": [
            t for t in [
                "<|startoftranscript|>", "<|endoftext|>", "<|transcribe|>",
                "<|notimestamps|>", "<|en|>", "<|yo|>", "<|ha|>", "<|ig|>", "<|pcm|>",
            ]
            if t not in tokenizer.get_vocab()
        ]
    })
    processor = WhisperProcessor(feature_extractor=fe, tokenizer=tokenizer)

vocab = processor.tokenizer.get_vocab()

LANG_TOKENS = {
    "yoruba":           "<|yo|>",
    "hausa":            "<|ha|>",
    "igbo":             "<|ig|>",
    "nigerian_english": "<|en|>",
    "pidgin":           "<|pcm|>",
}

def transcribe(audio_array, sampling_rate, language="yoruba"):
    lang_id = vocab[LANG_TOKENS[language]]
    start   = vocab["<|startoftranscript|>"]
    trans   = vocab["<|transcribe|>"]
    nots    = vocab["<|notimestamps|>"]
    decoder_input_ids = torch.tensor([[start, lang_id, trans, nots]])

    inputs = processor.feature_extractor(
        audio_array, sampling_rate=sampling_rate, return_tensors="pt"
    ).input_features

    with torch.no_grad():
        generated = model.generate(
            input_features=inputs,
            decoder_input_ids=decoder_input_ids,
            max_new_tokens=448
        )
    return processor.tokenizer.decode(generated[0], skip_special_tokens=True).strip()

---

📊 Benchmark Results

Evaluated on FLEURS test splits (Yoruba, Hausa, Igbo), Nigerian Pidgin ASR test set, and Nigerian Accented English dataset. 50 samples per language, greedy decoding, strict WER via jiwer (no text normalization). Identical methodology to V1 for direct comparison.

Lower WER = better. Human-level transcription ≈ 5–10%.

---

🛡️ Robustness Improvements over V1

SpecAugment

Frequency masking (up to 27 mel bins) and time masking (up to 100 time steps) applied to mel spectrograms during training. This prevents over-reliance on specific frequency bands or time positions, improving generalization to real-world recordings.

Noise Augmentation

30% of training samples received realistic background noise injection at random SNR levels before mel extraction. This directly trains the model for common Nigerian recording conditions — market noise, phone compression artifacts, outdoor ambient sound, and crowd audio.

Code-Switching Robustness

Trained on Nigerian Pidgin and Nigerian English together with Yoruba, Hausa, and Igbo — all of which contain natural code-switching patterns present in everyday Nigerian speech, media, and social content.

---

🎙️ Sample Transcriptions

Real audio samples from FLEURS test, Nigerian English, and Pidgin datasets — data the model never saw during training. Transcriptions generated by the published merged model.

Yoruba

Hausa

Igbo

Nigerian English

Nigerian Pidgin

---

🏗️ Model Architecture

Input Audio (16kHz)
        │
        ▼
Whisper-large-v3 Encoder  (frozen during fine-tuning)
        │  1500 × 1280 features
        ▼
Whisper Decoder + LoRA    (r=64, alpha=128, fine-tuned)
  target modules: q_proj, k_proj, v_proj, out_proj, fc1, fc2
  V1: attention only (q/k/v/out) — V2: adds feed-forward (fc1/fc2)
        │
        ▼
Extended Tokenizer         (vocab: 51,868 tokens)
  + <|ig|> Igbo token
  + <|pcm|> Nigerian Pidgin token
        │
        ▼
Transcript

V2 publishes a fully merged standalone model — no PEFT dependency required. Load directly with transformers.

---

📦 Training Details

Training Datasets

---

✅ Intended Use

• 🏦 Fintech & banking — voice transactions and customer service in Nigerian languages
• 📱 Mobile apps — voice input for Yoruba, Hausa, Igbo, and Pidgin speakers
• 🎙️ Media & journalism — transcribing interviews and broadcasts
• 🏥 Healthcare — patient intake and medical documentation
• 📚 Education — language learning tools and accessibility
• 🔬 Research — low-resource ASR study for West African languages
• ♿ Accessibility — assistive technology for Nigerians with disabilities

---

🚫 Prohibited Use

• ❌ Non-consensual surveillance — transcribing calls without consent of all parties
• ❌ Fraud facilitation — forging spoken statements or supporting advance-fee fraud
• ❌ Deepfake pipelines — combining with TTS to fake audio attributed to real people
• ❌ Discriminatory systems — denying services based on language or accent identification
• ❌ Political disinformation — generating or verifying false transcripts of political speech

---

👤 Creator

Emmanuel Ariyo (Ememzyvisuals) — Founder, Axiveri

NaijaVox is conceived, built, and trained by Emmanuel Ariyo — combining ML engineering with a Nigerian cultural design identity to bring open-weight speech recognition to Nigerian language speakers.

---

👥 About Axiveri

Axiveri is building Africa's AI infrastructure — open models, open data, and open tools for African languages and developers.

• 🌍 Axiveri on HuggingFace
• 🗣️ NaijaVox Collection

---

📄 Citation

@misc{naijavox2026,
  title        = {NaijaVox-2.0: Open-Weight Speech Recognition for Nigerian Languages},
  author       = {Ariyo, Emmanuel (Ememzyvisuals)},
  year         = {2026},
  publisher    = {HuggingFace},
  howpublished = {\url{https://huggingface.co/Axiveri/NaijaVox-2.0}}
}

---

📜 License

The model weights in this repository are released under the Apache License 2.0.

Training Data Notice

NaijaVox-2.0 was fine-tuned using multiple publicly available datasets obtained from their respective publishers and repositories. Each dataset remains subject to its own original license, attribution requirements, and terms of use.

This repository does not claim ownership of the underlying training datasets and does not modify or supersede the licenses governing those datasets. Users are responsible for reviewing and complying with the applicable terms of any datasets used during training.

If any dataset attribution or licensing information requires correction or clarification, please open an issue or contact the maintainers.

Responsible Use

NaijaVox-2.0 is intended for lawful and ethical automatic speech recognition applications. Users are expected to comply with all applicable laws, regulations, and the licenses governing both this repository and any underlying datasets.

<p align="center"> <i>Built in Nigeria 🇳🇬 — for Nigeria and the world.</i><br/> <i>Created by <a href="https://huggingface.co/ememzyvisuals">Emmanuel Ariyo (Ememzyvisuals)</a></i><br/> <i>Second model in the NaijaVox series by <a href="https://huggingface.co/Axiveri">Axiveri</a></i> </p>