UBC-NLP/Simba-TTS-lin

<div align="center">

<img src="https://africa.dlnlp.ai/simba/images/VoC_logo.png" alt="VoC Logo">

     

</div>

Bridging the Digital Divide for African AI

Voice of a Continent is a comprehensive open-source ecosystem designed to bring African languages to the forefront of artificial intelligence. By providing a unified suite of benchmarking tools and state-of-the-art models, we ensure that the future of speech technology is inclusive, representative, and accessible to over a billion people.

Best-in-Class Multilingual Models

<img src="https://africa.dlnlp.ai/simba/images/VoC_simba" alt="VoC Simba Models Logo">

Introduced in our EMNLP 2025 paper [Voice of a Continent](https://aclanthology.org/2025.emnlp-main.559/), the Simba Series represents the current state-of-the-art for African speech AI.

• —Unified Suite: Models optimized for African languages.
• —Superior Accuracy: Outperforms generic multilingual models by leveraging SimbaBench's high-quality, domain-diverse datasets.
• —Multitask Capability: Designed for high performance in ASR (Automatic Speech Recognition) and TTS (Text-to-Speech).
• —Inclusion-First: Specifically built to mitigate the "digital divide" by empowering speakers of underrepresented languages.

The Simba family consists of state-of-the-art models fine-tuned using SimbaBench. These models achieve superior performance by leveraging dataset quality, domain diversity, and language family relationships.

🔊 Simba-TTS (Text-to-Speech)

• —🎯 Task: Text-to-Speech — Natural Voice Synthesis. 🌍 Language Coverage (7 African languages)

Afrikaans (afr), Asante Twi (asanti), Akuapem Twi (akuapem), Lingala (lin), Southern Sotho (sot), Tswana (tsn), Xhosa (xho)

🧩 Usage Example

You can easily run inference using the Hugging Face transformers library.

from transformers import VitsModel, AutoTokenizer
import torch

model_name="Simba-TTS-afr" ## Simba-TTS-twi-asanti, Simba-TTS-twi-akuapem, Simba-TTS-lin, Simba-TTS-sot, Simba-TTS-tsn, Simba-TTS-xho
model = VitsModel.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

text = "Ons noem hierdie deeltjies sub-atomiese deeltjies" #example of Afrikaans (afr) language 
inputs = tokenizer(text, return_tensors="pt")

with torch.no_grad():
    output = model(**inputs).waveform

The resulting waveform can be saved as a .wav file:

scipy.io.wavfile.write("outputfile.wav", rate=model.config.sampling_rate, data=output.float().numpy())