mlsanityData to 14 Oct 2026

Whispering in Amharic: Fine-tuning Whisper for Low-resource Language

arXiv 2503.18485 ↗First posted 24 Mar 2025cs.CL cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

This work explores fine-tuning OpenAI's Whisper automatic speech recognition (ASR) model for Amharic, a low-resource language, to improve transcription accuracy. While the foundational Whisper model struggles with Amharic due to limited representation in its training data, we fine-tune it using datasets like Mozilla Common Voice, FLEURS, and the BDU-speech dataset. The best-performing model, Whispersmall-am, significantly improves when finetuned on a mix of existing FLEURS data and new, unseen Amharic datasets. Training solely on new data leads to poor performance, but combining it with FLEURS data reinforces the model, enabling better specialization in Amharic. We also demonstrate that normalizing Amharic homophones significantly enhances Word Error Rate (WER) and Bilingual Evaluation Understudy (BLEU) scores. This study underscores the importance of fine-tuning strategies and dataset composition for improving ASR in low-resource languages, providing insights for future Amharic speech recognition research.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 10 of its 25 references that are in the map. First posted on arXiv 24 Mar 2025.

Builds on

10 of 25 references.

References · 10

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 560
  3. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 469
  4. 2024The Revolution of Multimodal Large Language Models: A Surveycited by 137
  5. 2020Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approachcited by 83
  6. 2024Automatic Speech Recognition using Advanced Deep Learning Approaches: A surveycited by 50
  7. 2024Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Researchcited by 27
  8. 2023Natural Language Processing in Ethiopian Languages: Current State, Challenges, and Opportunitiescited by 11
  9. 2024Whispering in Norwegian: Navigating Orthographic and Dialectic Challengescited by 4
  10. 2024Improving Whisper's Recognition Performance for Under-Represented Language Kazakh Leveraging Unpaired Speech and Textcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Datacited by 7
  2. 2025Structured Sparsity and Weight-adaptive Pruning for Memory and Compute efficient Whisper modelscited by 1
  3. 2026Fine-tuning Whisper for Pashto ASR: strategies and scalecited by 0
  4. 2026Which Languages Transfer Best to Warlpiri? A Similarity-Based Study for Low-Resource ASRcited by 0
  5. 2026myMediWhisper: Construction of Burmese Medical Speech Corpus and Whisper Fine-Tuning for Clinical Dialogue ASRcited by 0