Low Language Transfer Speech-to-Text

A multilingual speech recogniser has heard much speech in its own languages. We ask how much of that it brings to a language it was never trained on, when it is fine-tuned on the little that language has. We score 28 open multilingual models untouched on Low-Language-TTS, 50 low-resource languages in 11 writing systems, and fine-tune 24 of them on at most 1,000 clips a language, 82 hours in all, with a dev set choosing every epoch. Fine-tuning lowers every model's macro character error rate (CER), by 16.6 to 53.1 points, to 9.5 at best, and a word language model takes three CTC models 1.2 to 1.4 points lower; WER is still 34.4 at best. On the 12 languages that no model lists, every model starts at 46 or worse and the best ends at 11.7. The same architectures from random weights stay 60 points or more behind, so the gain is transfer, and an encoder left untouched already gives a Whisper or Qwen decoder most of what it needs. It is the language, not the corpus: on FLEURS recordings that ours do not share, the median model keeps 79% of its gain. It costs the languages the models knew, 5.7 points of CER on English, Spanish, French and German in the median model. Low-rank adapters on 4% of the weights come within 1.1 points of tuning everything, and on 2 of 3 models forget less. Seq2seq and language-model decoders are done within three to five epochs, while a new CTC head is still improving at twenty or thirty. Data beats epochs: 25 clips a language take Qwen3-ASR 0.6B from 60.9 to 39.3, and at equal clips presented, ten times the data is worth 9.7 points. A model that first learned forty of the languages learns the other ten no faster. On a public Malay benchmark, untouched Whisper large-v3 scores 8.9 when it detects the language and 14.9 when told the clip is Malay, because it then translates the English that speakers mix in; trained on the Scicom telephony dataset it scores 6.0.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-12
DOI
https://doi.org/10.48550/arxiv.2611.16260
Primary Topic
Speech Recognition and Synthesis
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Low Language Transfer Speech-to-Text

Husein Zolkepli
arXiv (Cornell University)
Speech Recognition and Synthesis
preprint

Low Language Transfer Speech-to-Text

Husein Zolkepli
preprint en

Abstract

A multilingual speech recogniser has heard much speech in its own languages. We ask how much of that it brings to a language it was never trained on, when it is fine-tuned on the little that language has. We score 28 open multilingual models untouched on Low-Language-TTS, 50 low-resource languages in 11 writing systems, and fine-tune 24 of them on at most 1,000 clips a language, 82 hours in all, with a dev set choosing every epoch. Fine-tuning lowers every model's macro character error rate (CER), by 16.6 to 53.1 points, to 9.5 at best, and a word language model takes three CTC models 1.2 to 1.4 points lower; WER is still 34.4 at best. On the 12 languages that no model lists, every model starts at 46 or worse and the best ends at 11.7. The same architectures from random weights stay 60 points or more behind, so the gain is transfer, and an encoder left untouched already gives a Whisper or Qwen decoder most of what it needs. It is the language, not the corpus: on FLEURS recordings that ours do not share, the median model keeps 79% of its gain. It costs the languages the models knew, 5.7 points of CER on English, Spanish, French and German in the median model. Low-rank adapters on 4% of the weights come within 1.1 points of tuning everything, and on 2 of 3 models forget less. Seq2seq and language-model decoders are done within three to five epochs, while a new CTC head is still improving at twenty or thirty. Data beats epochs: 25 clips a language take Qwen3-ASR 0.6B from 60.9 to 39.3, and at equal clips presented, ten times the data is worth 9.7 points. A model that first learned forty of the languages learns the other ten no faster. On a public Malay benchmark, untouched Whisper large-v3 scores 8.9 when it detects the language and 14.9 when told the clip is Malay, because it then translates the English that speakers mix in; trained on the Scicom telephony dataset it scores 6.0.

arXiv (Cornell University)
Speech Recognition and Synthesis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon