Navajo Diné bizaad

ISO 639-1: nv ISO 639-3: nav I L

15,109 Words in vocabulary

3.72x Best compression

0.7658 Best isotropy

Sample text

Excerpts from Navajo Wikipedia articles.

Tółání Kʼish Chʼínítʼiʼ Tsé Chʼééchiiʼ yishtłizhii

Naakaii Dootłʼizhii Bikéyahdę́ę́ʼ lókʼaatah naaʼahóóhai Tsiiʼyishbizhí Dineʼé Bi...

Azeeʼ haajinítsoh Azeeʼ haajinítsʼóóz Azeeʼ haajiní łibáhígíí

The 20 most frequently used words in Navajo Wikipedia.

Explore Navajo interactively with browser-based demos.

Key metrics for all model types at a glance.

from wikilangs import tokenizer
tok = tokenizer('latest', 'nv', 32000)
tokens = tok.tokenize("Your text here")

from wikilangs import ngram
ng = ngram('latest', 'nv', gram_size=3)
score = ng.score("Your text here")

from wikilangs import markov
mc = markov('latest', 'nv', depth=3)
text = mc.generate(length=50)

from wikilangs import vocabulary
vocab = vocabulary('latest', 'nv')
info = vocab.lookup("word")

from wikilangs import embeddings
emb = embeddings('latest', 'nv', dimension=64)
vec = emb.embed_word("word")

Model Type	Variants	Description
Tokenizers	8k, 16k, 32k, 64k	BPE tokenizers with different vocabulary sizes
N-gram (Word)	2, 3, 4, 5-gram	Word-level language models
N-gram (Subword)	2, 3, 4, 5-gram	Subword-level language models
Markov (Word)	Depth 1–5	Word-level text generation
Markov (Subword)	Depth 1–5	Subword-level text generation
Vocabulary	—	Word dictionary with frequency and IDF
Embeddings	32d, 64d, 128d	Position-aware word embeddings