Skip to content
← Back to explorer

Nwāchā Munā: A Devanagari Speech Corpus and Proximal Transfer Benchmark for Nepal Bhasha ASR

Rishikesh Kumar Sharma, Safal Narshing Shrestha, Jenny Poudel, Rupak Tiwari, Arju Shrestha, Rupak Raj Ghimire, Bal Krishna Bal · Mar 8, 2026 · Citations: 0

Automatic Metrics
Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Mar 8, 2026, 9:35 AM

Recent

Extraction refreshed

Mar 14, 2026, 3:43 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.35

Abstract

Nepal Bhasha (Newari), an endangered language of the Kathmandu Valley, remains digitally marginalized due to the severe scarcity of annotated speech resources. In this work, we introduce Nwāchā Munā, a newly curated 5.39-hour manually transcribed Devanagari speech corpus for Nepal Bhasha, and establish the first benchmark using script-preserving acoustic modeling. We investigate whether proximal cross-lingual transfer from a geographically and linguistically adjacent language (Nepali) can rival large-scale multilingual pretraining in an ultra-low-resource Automatic Speech Recognition (ASR) setting. Fine-tuning a Nepali Conformer model reduces the Character Error Rate (CER) from a 52.54% zero-shot baseline to 17.59% with data augmentation, effectively matching the performance of the multilingual Whisper-Small model despite utilizing significantly fewer parameters. Our findings demonstrate that proximal transfer within South Asian language clusters serves as a computationally efficient alternative to massive multilingual models. We openly release the dataset and benchmarks to digitally enable the Newari community and foster further research in Nepal Bhasha.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction flags indicate low-signal or possible false-positive protocol mapping.
  • Extraction confidence is 0.35 (below strong-reference threshold).
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Persisted extraction missing

No explicit feedback protocol extracted.

Evidence snippet: Nepal Bhasha (Newari), an endangered language of the Kathmandu Valley, remains digitally marginalized due to the severe scarcity of annotated speech resources.

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: Nepal Bhasha (Newari), an endangered language of the Kathmandu Valley, remains digitally marginalized due to the severe scarcity of annotated speech resources.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: Nepal Bhasha (Newari), an endangered language of the Kathmandu Valley, remains digitally marginalized due to the severe scarcity of annotated speech resources.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Evidence snippet: Nepal Bhasha (Newari), an endangered language of the Kathmandu Valley, remains digitally marginalized due to the severe scarcity of annotated speech resources.

Reported Metrics

partial

Error rate, Cer, Jailbreak success rate

Confidence: Low Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: Fine-tuning a Nepali Conformer model reduces the Character Error Rate (CER) from a 52.54% zero-shot baseline to 17.59% with data augmentation, effectively matching the performance of the multilingual Whisper-Small model despite utilizing significantly fewer parameters.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: Nepal Bhasha (Newari), an endangered language of the Kathmandu Valley, remains digitally marginalized due to the severe scarcity of annotated speech resources.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Unknown
  • Expertise required: Multilingual
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.35
  • Flags: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

error ratecerjailbreak success rate

Research Brief

Deterministic synthesis

In this work, we introduce Nwāchā Munā, a newly curated 5.39-hour manually transcribed Devanagari speech corpus for Nepal Bhasha, and establish the first benchmark using script-preserving acoustic modeling. HFEPX signals include Automatic Metrics with confidence 0.35. Updated from current HFEPX corpus.

Generated Mar 14, 2026, 3:43 AM · Grounded in abstract + metadata only

Key Takeaways

  • In this work, we introduce Nwāchā Munā, a newly curated 5.39-hour manually transcribed Devanagari speech corpus for Nepal Bhasha, and establish the first benchmark using…
  • Fine-tuning a Nepali Conformer model reduces the Character Error Rate (CER) from a 52.54% zero-shot baseline to 17.59% with data augmentation, effectively matching the performance…

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Validate metric comparability (error rate, cer, jailbreak success rate).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Low-signal flag detected: protocol relevance may be indirect.

Research Summary

Contribution Summary

  • In this work, we introduce Nwāchā Munā, a newly curated 5.39-hour manually transcribed Devanagari speech corpus for Nepal Bhasha, and establish the first benchmark using script-preserving acoustic modeling.
  • Fine-tuning a Nepali Conformer model reduces the Character Error Rate (CER) from a 52.54% zero-shot baseline to 17.59% with data augmentation, effectively matching the performance of the multilingual Whisper-Small model despite utilizing…
  • We openly release the dataset and benchmarks to digitally enable the Newari community and foster further research in Nepal Bhasha.

Why It Matters For Eval

  • In this work, we introduce Nwāchā Munā, a newly curated 5.39-hour manually transcribed Devanagari speech corpus for Nepal Bhasha, and establish the first benchmark using script-preserving acoustic modeling.
  • We openly release the dataset and benchmarks to digitally enable the Newari community and foster further research in Nepal Bhasha.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: error rate, cer, jailbreak success rate

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote