Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Hello Afrika: Speech Commands in Kinyarwanda

Domaine:

natural language processing

Type de record:

papermodeldatasetsoftware
Créateur:
IgwAwoBleKad
Hôte:avatar
Voice or Speech Commands are a subset of the broader Spoken Word Corpus of a language which are essential for non-contact control of and activation of larger AI systems in devices used in everyday life especially for persons with disabilities. Currently, there is a dearth of speech command models for African languages. The Hello Afrika project aims to address this issue and its first iteration is focused on the Kinyarwanda language since the country has shown interest in developing speech recognition technologies culminating in one of the largest datasets on Mozilla Common Voice. The model was built off a custom speech command corpus made up of general directives, numbers, and a wake word. The final model was deployed on multiple devices (PC, Mobile Phone and Edge Devices) and the performance was assessed using suitable metrics. Data Science Africa, 2024

Visit

arxiv.org

Tasks

automatic speech recognitionspeech processing

Languages

Kinyarwanda

Tags

Audio and Speech ProcessingArtificial IntelligenceSound

Similaires

Kinyarwanda-speech-to-text-ASR/Kinyarwanda-speech-to-text-ASRParts of Speech in Kinyarwandayigagilbert/kinyarwanda-speech-trimmedbadrex/kinyarwanda-speech-500hbadrex/kinyarwanda-speech-samplebadrex/kinyarwanda-speech-1000h

Kinyarwanda-speech-to-text-ASR/Kinyarwanda-speech-to-text-ASR

Kinyarwanda Automatic Speech Recognition Model based on Whisper # KinyaWhisper - Kinyarwanda Automa

Parts of Speech in Kinyarwanda

Traditional grammar holds that parts of speech have broad semantic definitions: verbs are actions, n

yigagilbert/kinyarwanda-speech-trimmed

This dataset contains processed Kinyarwanda speech data with trimmed audio segments. The dataset co

badrex/kinyarwanda-speech-500h

This dataset contains 500 hours of transcribed Kinyarwanda speech data covering Health, Government,

badrex/kinyarwanda-speech-sample

This dataset contains a sample from the 500 hours of Kinyarwanda speech data covering Health, Govern

badrex/kinyarwanda-speech-1000h

This dataset contains ~1000 hours of transcribed Kinyarwanda speech data covering Health, Government