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

• URL: http://arxiv.org/abs/2603.07554v1
• Date: Sun, 08 Mar 2026 09:35:05 GMT
• Title: Nwāchā Munā: A Devanagari Speech Corpus and Proximal Transfer Benchmark for Nepal Bhasha ASR
• Abstract summary: We introduce Nwch Mun, a newly curated 5.39-hour manually transcribed Devanagari speech corpus for Nepal Bhasha.<n>We establish the first benchmark using script-preserving annotated acoustic modeling.
• Score: 0.9918851323801791
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• TharuChat: Bootstrapping Large Language Models for a Low-Resource Language via Synthetic Data and Human Validation [0.0]
  Tharu is an Indo-Aryan vernacular spoken by approximately 1.7 million people across the Terai belt of Nepal and India.<n>Despite a rich oral tradition, Tharu suffers from severe data scarcity and linguistic fragmentation.<n>This paper presents Tharu-LLaMA (3B), a specialized instruction-following model designed to address this exclusion.
  arXiv  Detail & Related papers  (2026-03-17T23:57:47Z)
• Simultaneous Speech-to-Speech Translation Without Aligned Data [52.467808474293605]
  Simultaneous speech translation requires translating source speech into a target language in real-time.<n>We propose Hibiki-Zero, which eliminates the need for word-level alignments entirely.<n>Hibiki-Zero achieves state-of-the-art performance in translation accuracy, latency, voice transfer, and naturalness across five X-to-English tasks.
  arXiv  Detail & Related papers  (2026-02-11T17:41:01Z)
• DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation [111.94720088481614]
  Can multimodal generative models effectively produce content given dialectal textual input?<n>We construct a new large-scale benchmark spanning six common English dialects.<n>We design a general encoder-based mitigation strategy for multimodal generative models.
  arXiv  Detail & Related papers  (2025-10-16T17:56:55Z)
• Exploring Cross-Lingual Knowledge Transfer via Transliteration-Based MLM Fine-Tuning for Critically Low-resource Chakma Language [1.4206084598312039]
  As an Indo-Aryan language with limited available data, Chakma remains largely underrepresented in language models.<n>We introduce a novel corpus of contextually coherent Bangla-transliterated Chakma, curated from Chakma literature, and validated by native speakers.<n>Experiments show that fine-tuned multilingual models outperform their pre-trained counterparts when adapted to Bangla-transliterated Chakma.
  arXiv  Detail & Related papers  (2025-10-10T06:07:14Z)
• Development of Pre-Trained Transformer-based Models for the Nepali Language [0.0]
  The Nepali language, spoken by approximately 32 million people worldwide, remains significantly underrepresented in this domain.<n>We have collected 27.5 GB of Nepali text data, approximately 2.4x larger than any previously available Nepali language corpus.<n>Our models outperformed the existing best model by 2 points on Nep-gLUE benchmark, scoring 95.60 and also outperformed existing models on text generation tasks.
  arXiv  Detail & Related papers  (2024-11-24T06:38:24Z)
• Abstractive Summarization of Low resourced Nepali language using Multilingual Transformers [0.0]
  The research addresses key challenges associated with summarizing texts in Nepali by first creating a summarization dataset through web scraping. The performance of the fine-tuned models were then assessed using ROUGE scores and human evaluation. The 4-bit quantized mBART with LoRA model was found to be effective in generating better Nepali news headlines.
  arXiv  Detail & Related papers  (2024-09-29T05:58:27Z)
• Low-Resource Counterspeech Generation for Indic Languages: The Case of Bengali and Hindi [11.117463901375602]
  We bridge the gap for low-resource languages such as Bengali and Hindi. We create a benchmark dataset of 5,062 abusive speech/counterspeech pairs. We observe that the monolingual setup yields the best performance.
  arXiv  Detail & Related papers  (2024-02-11T18:09:50Z)
• Optimal Transport Posterior Alignment for Cross-lingual Semantic Parsing [68.47787275021567]
  Cross-lingual semantic parsing transfers parsing capability from a high-resource language (e.g., English) to low-resource languages with scarce training data. We propose a new approach to cross-lingual semantic parsing by explicitly minimizing cross-lingual divergence between latent variables using Optimal Transport.
  arXiv  Detail & Related papers  (2023-07-09T04:52:31Z)
• AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages [75.08199398141744]
  We present AmericasNLI, an extension of XNLI (Conneau et al.), to 10 indigenous languages of the Americas. We conduct experiments with XLM-R, testing multiple zero-shot and translation-based approaches. We find that XLM-R's zero-shot performance is poor for all 10 languages, with an average performance of 38.62%.
  arXiv  Detail & Related papers  (2021-04-18T05:32:28Z)
• Multilingual Speech Translation with Efficient Finetuning of Pretrained Models [82.22294901727933]
  A minimalistic LNA (LayerNorm and Attention) finetuning can achieve zero-shot crosslingual and cross-modality transfer ability. Our approach demonstrates strong zero-shot performance in a many-to-many multilingual model.
  arXiv  Detail & Related papers  (2020-10-24T08:15:08Z)
• Unsupervised Cross-lingual Representation Learning for Speech Recognition [63.85924123692923]
  XLSR learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build on wav2vec 2.0 which is trained by solving a contrastive task over masked latent speech representations. Experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining.
  arXiv  Detail & Related papers  (2020-06-24T18:25:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.