← Back to all news
arXiv Computation and Language By Leonardo Duart, Tiago Fonseca, Thiago Chac\'on

Fine-Tuning Whisper for Automatic Speech Recognition in Baniwa: A Preliminary Study

Read the original on arXiv Computation and Language →

The study fine‑tunes the Whisper Small model for Automatic Speech Recognition (ASR) in Baniwa, an indigenous Arawakan language. Using a 0.54‑hour corpus of 1,373 manually transcribed recordings, the fine‑tuned model achieved a Word Error Rate of 37.5% and a Character Error Rate of 7.45%. These results provide an initial baseline for Baniwa ASR and suggest that multilingual foundation models can be adapted to extremely low‑resource languages.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Sep 25

Benchmarking and Domain Adaptation of Automatic Speech Recognition (ASR) for Adolescent Health Communication in Ghanaian Languages

This study evaluates automatic speech recognition (ASR) for adolescent health communication in Twi, Dagbani, and Ewe by benchmarking five ASR systems on a Bible corpus and a domain-specific ASRH dataset, then performing supervised domain adaptation with a fine‑tuned Qwen3-ASR-0.6B model. Fine‑tuning significantly lowered word and character error rates, especially for Ewe, and the adapted model was deployed in the KasaHealth voice‑first application, which received high user approval and highlighted remaining domain gaps. The work demonstrates that in‑domain data, rather than model size or computational resources, is the primary limitation for effective ASR in these languages.

By Stephen E. Moore, Akwasi Asare, Mich-Seth Owusu, Paul Azunre, Joel Budu, Lawrence A. Adu-Gyamfi
llmsfine-tuningmultimodalbenchmarks
More like this →
arXiv Computation and Language
Sep 7

Automatic Speech Recognition for Multilingual Oral History Research

The paper examines how Automatic Speech Recognition (ASR) tools, particularly Whisper, are being used in community-led heritage language preservation, focusing on Cantonese oral histories in New Zealand. It reports that the best Whisper configuration achieved a 12.10 % Word Error Rate (WER) but struggled with non‑English segments, yet it can produce a first‑pass transcription in only 1 % of the time required for manual transcription.

By Sidney Wong, Chelsea Wong She, Eda Tang, Tiana Marshall Wong, Debbie Sew Hoy, Chelsea Wong
multimodal
More like this →