diff --git a/gnu/packages/machine-learning.scm b/gnu/packages/machine-learning.scm index 072fb1ab15..402a8226b5 100644 --- a/gnu/packages/machine-learning.scm +++ b/gnu/packages/machine-learning.scm @@ -611,6 +611,25 @@ (define-public sentencepiece depend on language-specific pre- or post-processing.") (license license:asl2.0))) +(define-public python-sentencepiece + (package + (name "python-sentencepiece") + (version "0.1.97") + (source + (origin + (method url-fetch) + (uri (pypi-uri "sentencepiece" version)) + (sha256 + (base32 "0v0z9ryl66432zajp099bcbnwkkldzlpjvgnjv9bq2vi19g300f9")))) + (build-system python-build-system) + (native-inputs (list pkg-config)) + (propagated-inputs (list sentencepiece)) + (home-page "https://github.com/google/sentencepiece") + (synopsis "SentencePiece python wrapper") + (description "This package provides a Python wrapper for the SentencePiece +unsupervised text tokenizer.") + (license license:asl2.0))) + (define-public shogun (package (name "shogun")