While several pre-trained multilingual models are actively used for fine-tuning on under-resourced and endangered languages, it remains unclear which architectures perform better and what factors explain their varying performance across languages. Although this question may be less pressing for languages with adequate resources, it is critical for endangered language communities, where limited time and funding to experiment with multiple model options are available (Jimerson et al., 2023). We compare the performance of two ASR architectures, Wav2Vec2 and Whisper, on a Dënë Sųłıné dataset. This language and dataset present several challenges common to under-resourced and endangered languages: unstandardized orthography, pronunciation variation, and phonological and morphosyntactic structures that differ from the major languages represented in the multilingual datasets used for pre-training large ASR models. Although Wav2Vec2 reportedly outperforms Whisper in low-resource settings (see e.g., Coto-Solano et al., 2024; Nahabwe et al., 2025; Williams et al., 2023), our study shows that Whisper yields significantly better results on the Dënë Sųłıné dataset. These findings suggest that model performance may depend not only on architecture, dataset size, or typological features of language, but also on dataset-specific characteristics. In our case, Whisper showed better adaptability to a dataset with inconsistent spelling and pronunciation. Further verification across similarly inconsistent datasets is required to assess the generalizability of this result.

While machine learning approaches dominate contemporary NLP research, a critical gap exists between published models and tools actually used by target communities (Gessler & von der Wense, 2024). This paper presents two morphological parsers for Media Lengua (ISO 639-3: mue), an endangered mixed language of Ecuador, demonstrating that a JavaScript rule-based system (98.6% accuracy) can outperform a CRF model (95.7% F1) while offering immediate community accessibility.Not all language structures permit straightforward rule-based parsing; however, when a language’s morphology allows for this approach with competitive accuracy, we argue that it should be preferred for its practical advantages: immediate browser-based deployment, transparency, zero infrastructure requirements, and long-term maintainability. Our rule-based parser runs entirely in the browser, is freely available online, and can be adapted to other Quechuan languages. In contrast, while the CRF model performs well on benchmarks, it requires additional infrastructure to become accessible.Our comparison highlights the need to evaluate NLP tools not only on accuracy metrics but also on accessibility and real-world adoption, which is particularly crucial for endangered language communities where sustainable, community-accessible tools can support language documentation, education, and revitalization.

This paper presents a study focused on advancing Automatic Speech Recognition (ASR) for the under-resourced language Dënë Sųłıné through data-centric approaches. We explore multiple strategies to enhance the quality of training data—both audio recordings and transcriptions—to address the challenges posed by mixed-quality datasets. Our experiments investigate which data preparation techniques most effectively improve ASR performance in this context. Our findings show that reducing non-phonemic spelling variation in the corpus significantly improves model generalization, resulting in a substantial increase in recognition accuracy. Additionally, we demonstrate that increasing manually reviewed transcriptions consistently improves word and character error rates, while audio enhancement slightly reduces performance, highlighting the complex trade-offs in low-resource ASR development.

This paper describes the process and learn- ing outcomes of a three-day workshop on ma- chine learning basics for documentary linguists. During this workshop, two groups of linguists working with two Indigenous languages of North America, Blackfoot and Dënë Su ̨łıné, became acquainted with machine learning prin- ciples, explored how machine learning can be used in data processing for under-resourced languages and then applied different machine learning methods for automatic morphologi- cal interlinearization and parts-of-speech tag- ging. As a result, participants discovered paths to greater collaboration between computer sci- ence and documentary linguistics and reflected on how linguists might be enabled to apply ma- chine learning with less dependence on experts.

Plains Cree (nêhiyawêwin) is a morphologically complex and predominantly prefixing language. The combinatory potential of inflectional and derivational/lexical prefixes and verb stems in Plains Cree makes it challenging for traditional auto-completion (or word suggestion) approaches to handle. The lack of a large corpus of Plains Cree also complicates the situation. This study attempts to investigate how well a BiLSTM model trained on a small Cree corpus can handle a word suggestion task. Moreover, this study evaluates whether the use of semantically and morphosyntactically refined Word2Vec embeddings can improve the overall accuracy and quality of BiLSTM suggestions. The results show that some models trained with the refined vectors provide semantically and morphosyntactically better suggestions. They are also more accurate in predictions of content words. The model trained with the non-refined vectors, in contrast, was better at predicting conjunctions, particles, and other non-inflecting words. The models trained with different refined vector combinations provide the expected next word among top-10 predictions in 36.73 to 37.88% of cases (depending on the model).