Skip to content
AI News HubLIVE
Original source2 min read

Comparative Analysis of Multilingual Pre-trained Models for Nepali Automatic Speech Recognition

Summary

A controlled benchmark fine-tunes six pretrained speech models on the ~165-hour OpenSLR SLR54 Nepali corpus under one protocol, finding Whisper-Large-v3-Turbo and IndicWav2Vec tied at the top and CTC decoders up to 29x faster at equal accuracy.

SourcearXiv Computational LinguisticsAuthor: Suman Paudel, Sarbin Sayami
Comparative Analysis of Multilingual Pre-trained Models for Nepali Automatic Speech Recognition
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 31 May 2026]

Title:Comparative Analysis of Multilingual Pre-trained Models for Nepali Automatic Speech Recognition

View a PDF of the paper titled Comparative Analysis of Multilingual Pre-trained Models for Nepali Automatic Speech Recognition, by Suman Paudel and Sarbin Sayami

View PDF HTML (experimental)

Abstract:Multilingual pretrained models nominally support Nepali, yet no controlled benchmark has compared them under a single fine-tuning protocol. We fine-tune six pretrained models (XLSR-53, IndicWav2Vec, MMS-1B, Whisper-Medium, Whisper-Large-v3-Turbo, and Conformer-Hi) spanning CTC self-supervised, autoregressive encoder-decoder, and hybrid Conformer-CTC architectures, on the OpenSLR SLR54 Nepali corpus (~165 hours) using identical preprocessing, splits, optimizer, and family-matched learning-rate schedules. We evaluate Word Error Rate (WER), Character Error Rate (CER), and Real-Time Factor (RTF) on three independent test sets (OpenSLR, FLEURS, Common Voice). Whisper-Large-v3-Turbo (14.76% WER) and IndicWav2Vec (14.89% WER) tie at the top despite a 9x parameter gap and 40x pretraining-data gap, providing direct empirical evidence that language-family proximity in pretraining can substitute for raw scale for in-domain Nepali. CTC decoders run up to 29x faster than autoregressive Whisper at the same accuracy, flipping the practical deployment preference toward CTC under any latency budget. Massively multilingual pretraining (MMS-1B) yields the smallest out-of-domain degradation on FLEURS (+12.55 pp), indicating that scale buys robustness rather than peak in-domain accuracy. The resulting benchmark provides the first standardized, multi-model, efficiency-aware reference numbers for Nepali ASR.

Comments: 9 pages, 6 figures, 7 tables. Based on this http URL. thesis (Institute of Science and Technology, Tribhuvan University). Code and models: this https URL

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Cite as: arXiv:2608.12327 [cs.CL]

(or arXiv:2608.12327v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2608.12327

arXiv-issued DOI via DataCite

Submission history

From: Suman Paudel [view email] [v1] Sun, 31 May 2026 12:05:48 UTC (84 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Comparative Analysis of Multilingual Pre-trained Models for Nepali Automatic Speech Recognition, by Suman Paudel and Sarbin Sayami

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-08

Change to browse by:

cs cs.AI cs.LG

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Whisper-Large-v3-Turbo (14.76% WER) and IndicWav2Vec (14.89% WER) tie at the top despite a 9x parameter gap and 40x pretraining-data gap
  • CTC decoders run up to 29x faster than autoregressive Whisper at the same accuracy, favoring CTC for latency-sensitive deployment
  • MMS-1B shows the smallest out-of-domain degradation on FLEURS (+12.55 pp), indicating scale buys robustness rather than peak in-domain accuracy
  • The benchmark provides the first standardized, multi-model, efficiency-aware reference numbers for Nepali ASR

Highlights and analysis are generated automatically and may contain errors. Check the original source.