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.

From Speech to Text Corpora: Evaluating ASR-Based Data Acquisition for Low-Resource Fongbe and Hausa

Domaine:

natural language processing

Type de record:

paperdataset
Créateur:
AdjOluEiselen, RoaldMit
Hôte:avatar
Low-resource African languages lack text corpora needed for language model training. We investigate whether ASR pipelines can extend text resources for two typologically distinct West African languages: Fongbe (tonal, diacritic-rich) and Hausa (non-tonal). We fine-tune MMS-300M on a curated 12.3-hour Fongbe dataset, achieving 9.48% WER on the ALFFA benchmark - a 78% relative reduction from the prior 44.04% baseline - while preserving tonal diacritics critical to the language. For Hausa, we apply an existing fine-tuned Whisper-Small model. We catalog 1,553 YouTube videos (236 hours) and process a subset of 424 videos (45.49 hours) selected to balance domain diversity with available computational resources, producing 6,770 transcribed segments. Human evaluation on 50 randomly sampled segments per language shows mean quality scores of 57.4/100 for Hausa and 36.5/100 for Fongbe, indicating that while Hausa transcriptions approach acceptable quality for corpus construction, Fongbe transcriptions require post-processing or improved models for production use. We release the curated dataset, fine-tuned model, transcribed corpus, and full video catalog following platform terms and ethical guidelines. 10 pages, 1 figure, 4 tables

Visit

arxiv.org

Tasks

automatic speech recognitionspeech processing

Languages

FonHausa

Tags

Computation and LanguageArtificial IntelligenceMachine LearningI.2.7

Similaires

Text-To-Speech Data Augmentation for Low Resource Speech RecognitionFrom Translation to Retrieval: Evaluating LLM-Based Information Retrieval for Hausa and Fongbe Text-to-Speech Synthesis Using Found Data for Low-Resource LanguagesAdversarial Text-to-Speech for low-resource languagesosinkolu/fongbe-hausa-asrStrategies for improving low resource speech to text translation relying on pre-trained ASR models

Text-To-Speech Data Augmentation for Low Resource Speech Recognition

Nowadays, the main problem of deep learning techniques used in the development of automatic speech r

From Translation to Retrieval: Evaluating LLM-Based Information Retrieval for Hausa and Fongbe

Text-to-Speech Synthesis Using Found Data for Low-Resource Languages

Text-to-speech synthesis is a key component of interactive, speech-based systems. Typically, buildi

Adversarial Text-to-Speech for low-resource languages

Improving the adversarial TTS models for low-resource languages by utilizing the high-frequency similarities between the different languages.

osinkolu/fongbe-hausa-asr

# Fongbe ASR Dataset Creator A pipeline for building a unified Automatic Speech Recognition (ASR) d

Strategies for improving low resource speech to text translation relying on pre-trained ASR models

This paper presents techniques and findings for improving the performance of low-resource speech to