kaldingram

kaldingram provides Python and CLI tools to:

The implementation is based on Kaldi WSJ scripts and matches SRILM-style behavior.

Install

pip install kaldingram

kaldingram train --ngram-order 4 --text corpus.txt --lm 4gram.arpa

Or stream text from stdin and write ARPA to stdout:

cat corpus.txt | kaldingram train --ngram-order 3 > 3gram.arpa

kaldingram prune --threshold 1e-8 --lm 4gram.arpa --write-lm 4gram_pruned.arpa

kaldingram ppl --lm 4gram.arpa --text test.txt
cat test.txt | kaldingram ppl --lm 4gram.arpa

Build package locally:

python -m pip install --upgrade build
python -m build

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

kaldingram-0.1.1.tar.gz (14.1 kB view details)

Uploaded Jul 6, 2026 Source

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

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

Uploaded Jul 6, 2026 Python 3

Details for the file kaldingram-0.1.1.tar.gz.

Hashes for kaldingram-0.1.1.tar.gz
Algorithm	Hash digest
SHA256	`eef54c73816c6cad4a9d2522cb00a2f00101f8cc9d9306c42d8006224dd31f1a`
MD5	`2a7fb0f13b32f68cff10c5767c1be48a`
BLAKE2b-256	`8b6f603aa9f5e8048777129cc86f320c79ffca2ffe7fef41102886448cbf3ddb`

Details for the file kaldingram-0.1.1-py3-none-any.whl.

Hashes for kaldingram-0.1.1-py3-none-any.whl
Algorithm	Hash digest
SHA256	`5d44b996866462cdb038434e5bc235ad7dd356d9dea4b9e4b84811ae3d4f8adc`
MD5	`d8b139cc5450272a3c45ad84117e778b`
BLAKE2b-256	`2709107fed74e799df572eb99bb70531d675f67ec135bbf2cf4e9ec937c4fee9`