bpemb
Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE).
bheinzerling/bpemb is ranked 11,067 with 1,227 stars.
bheinzerling/bpemb is ranked 11,067 among these 8 peers; MoonshotAI/Kimi-VL is ranked 11,064.
| Name | Rank | Metrics |
|---|---|---|
| PlayVoice/vits_chinese | 11,047 |
|
| Tencent-Hunyuan/HunyuanCustom | 11,048 |
|
| qubvel/classification_models | 11,051 |
|
| MoonshotAI/Kimi-VL | 11,064 |
|
| TencentGameMate/chinese_speech_pretrain | 11,109 |
|
| Tencent-Hunyuan/HunyuanWorld-Mirror | 11,113 |
|
| UMass-Embodied-AGI/3D-LLM | 11,117 |
|
| hgneng/ekho | 11,121 |
|
| Parameter | Value |
|---|---|
| Language | Python |
| Category | Models |
| Stars | 1,227 |
| Forks | 100 |
| Contributors | 6 |
| Created date | 2017-10-04 |
| Updated date | 2026-10-13 |
| Stars in 1 day | 0 |
| Stars in 7 days | 3 |
| Rank | 11,067 |
| Previous rank | 11,021 |
| Rank change | -46 |
| 7-day stars rank | 7,010 |
| Previous 7-day stars rank | 7,038 |
| 7-day stars rank change | 28 |
| Total stars rank | 9,524 |
| Previous total stars rank | 9,517 |
| Total stars rank change | -7 |
| Country | Japan |
BPEmb BPEmb is a collection of pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) and trained on Wikipedia. Its intended use is as input for neural models in natural language processing. Website ・ Usage ・ Download ・ MultiBPEmb ・ Paper (pdf) ・ Citing BPEmb Usage Install BPEmb with pip: Embeddings and SentencePiece models will be downloaded automatically the first time you use them. The first is subword segmentation: If / how a word gets split depends on the vocabulary size.
How many stars and forks are recorded?
bheinzerling/bpemb has 1,227 stars and 100 forks.
What is the repository rank?
bheinzerling/bpemb is ranked 11,067.
What language and category are recorded?
bheinzerling/bpemb has 1,227 stars, uses Python and belongs to Models.
Which repository is closest in rank?
bheinzerling/bpemb is compared with MoonshotAI/Kimi-VL, ranked 11,064 with 1,227 stars.