paper-with-me

홈 › Papers

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

2025-03-24 · Dawit Ketema Gete, Bedru Yimam Ahmed, Tadesse Destaw Belay, Yohannes Ayana Ejigu, Sukairaj Hafiz Imam, Alemu Belay Tessema, Mohammed Oumer Adem, Tadesse Amare Belay, Robert Geislinger, Umma Aliyu Musa, Martin Semmann, Shamsuddeen Hassan Muhammad, Henning Schreiber, Seid Muhie Yimam

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.

📄 PDF Abstract BibTeX arXiv:2503.18485

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Whispering in Norwegian: Navigating Orthographic and Dialectic Challenges

2024-02-02 · Per E Kummervold, Javier de la Rosa, Freddy Wetjen, Rolv-Arild Braaten 외

This article introduces NB-Whisper, an adaptation of OpenAI's Whisper, specifically fine-tuned for Norwegian language Automatic Speech Recognition (ASR). We highlight its key contributions and summarise the results achie…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

A processing framework to access large quantities of whispered speech found in ASMR

2023-03-13 · Pablo Perez Zarazaga, Gustav Eje Henter, Zofia Malisz

Whispering is a ubiquitous mode of communication that humans use daily. Despite this, whispered speech has been poorly served by existing speech technology due to a shortage of resources and processing methodology. To re…

Action DetectionActivity Detection

Whispering to a Blackbox: Bootstrapping Frozen OCR with Visual Prompts

2026-03-05 · Samandar Samandarov, Nazirjon Ismoiljonov, Abdullah Sattorov, Temirlan Sabyrbayev arxiv

In the landscape of modern machine learning, frozen pre-trained models provide stability and efficiency but often underperform on specific tasks due to mismatched data distributions. This paper introduces the Whisperer, …

Reinforcement Learning

End-to-end Whispered Speech Recognition with Frequency-weighted Approaches and Pseudo Whisper Pre-training

2020-05-05 · Heng-Jui Chang, Alexander H. Liu, Hung-Yi Lee, Lin-shan Lee

Whispering is an important mode of human speech, but no end-to-end recognition results for it were reported yet, probably due to the scarcity of available whispered speech data. In this paper, we present several approach…

speech-recognitionSpeech RecognitionTransfer Learning

Walia-LLM: Enhancing Amharic-LLaMA by Integrating Task-Specific and Generative Datasets

2024-02-12 · Israel Abebe Azime, Atnafu Lambebo Tonja, Tadesse Destaw Belay, Mitiku Yohannes Fuge 외

Large language models (LLMs) have received a lot of attention in natural language processing (NLP) research because of their exceptional performance in understanding and generating human languages. However, low-resource …

Language ModelingLanguage Modelling