Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

AfriVox-Translate: An African benchmark dataset for Automatic Speech Translation

Domain:

natural language processing

Record type:

dataset
Creator:
int
Host:
This project creates a benchmark dataset for evaluating Automatic Speech Translation models on African languages. This benchmark dataset combines AST test sets from multiple domain and sources for 20 African languages. See source and language details below. License

Visit

huggingface.co

Tasks

machine translationspeech processingspeech translation

Languages

AfrikaansAkanAmharicFulaGaGandaHausaIgboKinyarwandaSetswana+7

Similar

AfriVox: An African benchmark dataset for Automatic Speech Translation and Speech RecognitionKARAKALPAK SPEECH CORPUS: THE FIRST BENCHMARK DATASET FOR AUTOMATIC SPEECH RECOGNITIONAfriVox-v2: A Domain-Verticalized Benchmark for In-the-Wild African Speech Recognition

AfriVox: An African benchmark dataset for Automatic Speech Translation and Speech Recognition

This project creates a benchmark dataset for evaluating Automatic Speech Translation and Speech reco

KARAKALPAK SPEECH CORPUS: THE FIRST BENCHMARK DATASET FOR AUTOMATIC SPEECH RECOGNITION

While large-scale pre-trained models have significantly advanced multilingual Automatic Speech Recog

AfriVox-v2: A Domain-Verticalized Benchmark for In-the-Wild African Speech Recognition

Recent large language models (LLMs) show strong speech recognition and translation capabilities for