Skip to main content

ailia Tokenizer

Project description

ailia Tokenizer Python API

!! CAUTION !! “ailia” IS NOT OPEN SOURCE SOFTWARE (OSS). As long as user complies with the conditions stated in License Document, user may use the Software for free of charge, but the Software is basically paid software.

About ailia Tokenizer

The ailia Tokenizer is an NLP tokenizer that can be used from Unity or C++. The tokenizer is an API for converting text into tokens (sequences of symbols) that AI can handle, or for converting tokens back into text.

Traditionally, tokenization has been performed using Pytorch's Transformers. However, since Transformers only work with Python, there has been an issue of not being able to tokenize from applications on Android or iOS.

With ailia Tokenizer, this problem is solved by directly performing NLP tokenization without using Pytorch's Transforms. This makes it possible to perform tokenization on Android and iOS as well.

Since ailia Tokenizer includes Mecab and SentencePiece, it is possible to perform complex tokenizations, such as those for BERT Japanese or Sentence Transformer, on the device.

Install from pip

You can install the ailia SDK free evaluation package with the following command.

pip3 install ailia_tokenizer

Install from package

You can install the ailia SDK from Package with the following command.

python3 bootstrap.py
pip3 install .

API specification

https://github.com/ailia-ai/ailia-sdk

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ailia_tokenizer-1.6.1.tar.gz (20.2 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ailia_tokenizer-1.6.1-py3-none-any.whl (20.5 MB view details)

Uploaded Python 3

File details

Details for the file ailia_tokenizer-1.6.1.tar.gz.

File metadata

  • Download URL: ailia_tokenizer-1.6.1.tar.gz
  • Upload date:
  • Size: 20.2 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.13

File hashes

Hashes for ailia_tokenizer-1.6.1.tar.gz
Algorithm Hash digest
SHA256 31e931be2178315791857caf0440c435d1224586352381a95fd5b60e6c5b0378
MD5 f139d93b4c62fabd56d27f4e84fefbd8
BLAKE2b-256 e799249582d68a6696b0d6f1d6612898c125d9365a95b586ebf4661825cf8848

See more details on using hashes here.

File details

Details for the file ailia_tokenizer-1.6.1-py3-none-any.whl.

File metadata

File hashes

Hashes for ailia_tokenizer-1.6.1-py3-none-any.whl
Algorithm Hash digest
SHA256 fe359a677377b0fb0fa69931e061feb934fdd5d27cfb2a48687bf878aea6d1f3
MD5 1da5c4d21a0ee705e33577e2bc6b343a
BLAKE2b-256 82ee068c8a302262cea290ce09eb5741fb9222f10c5bc479a1a7dd4b89a846e0

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page