
This is a comparison between fasttext and word2vec, as well as execution and learning scripts.
Description in other languages
Statistics
Statistics as of Nov 17, 2026
GitHub stars
48
±0 (Oct 13〜)
Last commit
Aug 2017
Created on GitHub
Mar 30, 2017
Listed
Sep 13, 2022
Stars over time
Show as a table
| Month | Stars |
|---|---|
| Dec 2025 | 49 |
| Jan 2026 | 49 |
| Feb 2026 | 48 |
| Mar 2026 | 48 |
| Apr 2026 | 48 |
| May 2026 | 48 |
| Jun 2026 | 48 |
| Jul 2026 | 48 |
| Aug 2026 | 48 |
| Sep 2026 | 48 |
| Oct 2026 | 48 |
| Nov 2026 | 48 |
Last snapshot of each month. Star counts of 1,000 or more are rounded to the nearest 100.
Popular in the same category
JGLUEyahoojapan349JGLUE: Japanese General Language Understanding Evaluation
llm-jp-evalllm-jp175This tool is designed to automatically evaluate large-scale Japanese language models across multiple datasets.
jp-stabletree155JP Language Model Evaluation Harness
t5-japanesesonoisa117Japanese T5 model
llm-lora-classificationhppRC97llm-lora-classification
japanese-lm-fin-harnesspfnet-research80Japanese Language Model Financial Evaluation Harness
Resources in similar research fields
japanese-words-to-vectorsphilipperemy87Word2vec (word to vectors) approach for Japanese language using Gensim and Mecab.Shared: Representation Learning・Semantic Text Processing- ruri-v3-310mcl-nagoya634kRuri v3 is a state‑of‑the‑art Japanese text‑embedding model built on ModernBERT‑Ja, supporting up to 8,192‑token inputs, a 100K‑token vocabulary, FlashAttention‑accelerated inference, and multiple size variants for fast sentence‑transformer usage.HF modelShared: Representation Learning・Semantic Text Processing
- ruri-v3-30mcl-nagoya126kRuri v3 is a state‑of‑the‑art Japanese text embedding model built on ModernBERT‑Ja, supporting up to 8,192 tokens, a 100 k‑token vocabulary, FlashAttention acceleration, and multiple sizes from 37 M to 315 M parameters.HF modelShared: Representation Learning・Semantic Text Processing
- ruri-v3-130mcl-nagoya93kRuri v3 is a state‑of‑the‑art Japanese text‑embedding model built on ModernBERT‑Ja, supporting up to 8192‑token sequences, a 100K‑token vocabulary, FlashAttention, and released in sizes from 30 M to 310 M parameters for use with sentence‑transformers.HF modelShared: Representation Learning・Semantic Text Processing
chiVeWorksApplications179Japanese word embedding with Sudachi and NWJCShared: Representation Learning・Semantic Text Processing- bert-large-japanese-v2tohoku-nlp66kJapanese‑BERT‑Large trained on CC‑100 and Wikipedia, using Unidic‑lite word‑level tokenization with WordPiece subwords and whole‑word masking (24 layers, 1024‑dim hidden, 16 heads, 32k vocab), with pretraining code on cl‑tohoku/bert‑japanese.HF modelShared: Representation Learning・Semantic Text Processing