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.

asr-africa/African-ASR-Domain-Adaptation-Evaluation

Domaine:

natural language processing

Type de record:

dataset
Créateur:
asr
Hôte:
This dataset forms the the Africa ASR domain adaptation benchmark. The goal of the dataset is to enable building of ASR models for African languages that can adapt to domians outside the training data. The benchmark is made up of 2 languages, Wolof and Akan.

Visit

huggingface.co

Tasks

automatic speech recognitionspeech processing

Languages

Wolof

Similaires

asr-africa/African-ASR-Speech-Type-AdaptationJONAHKYAGABA/African-Language-ASR-Model-EvaluationDomain Adaptation in Low-Resource Perso-Arabic ASR with XLSR-53 Pre-Trainingasr-africa/wav2vec2-asr-africa-baseSOA: Reducing Domain Mismatch in SSL Pipeline by Speech Only Adaptation for Low Resource ASRdjelia/bambara-asr-evaluation

asr-africa/African-ASR-Speech-Type-Adaptation

JONAHKYAGABA/African-Language-ASR-Model-Evaluation

African Language ASR Model Evaluation # 🌍 African Language ASR Model Evaluation This project provi

Domain Adaptation in Low-Resource Perso-Arabic ASR with XLSR-53 Pre-Training

Self-supervised pre-training could effectively improve the performance of low-resource automatic spe

asr-africa/wav2vec2-asr-africa-base

SOA: Reducing Domain Mismatch in SSL Pipeline by Speech Only Adaptation for Low Resource ASR

Recently, speech foundation models have gained popularity due to their superiority in finetuning dow

djelia/bambara-asr-evaluation