No project description provided
Project description
ngram-lm
Installation
pip install ngram-lm
Usage
Given some ARPA file, a trie can be built like this:
from ngram_lm.trie import build
lm_order = 3
arpa_path = "/path/to/arpa-file"
out_path = "/the/desired/output/path/where/trie/will/be/saved"
build(lm_order, arpa_path, out_path)
Then, the trie can be loaded into memory and queried:
from ngram_lm.trie import Trie
t = Trie(out_path)
context = ["ele", "foi"]
n_predictions = 5
predictions = t.next_word_predictions(context, n_predictions)
for p in predictions:
print(p)
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distributions
Close
Hashes for ngram_lm-0.1.0-pp37-pypy37_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | baa7452e692d6e250b6f6a54903e6cfede69e2d943884aff8657806655b1058d |
|
MD5 | a16e025b582d7b0cac301058d58a7693 |
|
BLAKE2b-256 | ea969fd4077885de823af97f6da2c50e693a37cf48795f6404943616342d3692 |
Close
Hashes for ngram_lm-0.1.0-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 4b2fe3a79b1259756e6d34c5be4f836bb1b70c37a6f0c687eaa6c113e68c028d |
|
MD5 | 166b093bcda2802b78e4fe699a6ee3ec |
|
BLAKE2b-256 | d62c9a86cf3f01a7575310288ce529c8859136c137f2bb41a808d77dbc482777 |
Close
Hashes for ngram_lm-0.1.0-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 15bf91c579296111515b73e29cd9f7fd2e7968e6a1e5a978216946a4c7b1dc12 |
|
MD5 | 8b95761c3c4d3582ef0213cf557059a9 |
|
BLAKE2b-256 | 69ab972baec2e3d2f60a6257833b576a32d281bfdf5bad7edf4697a600c97518 |
Close
Hashes for ngram_lm-0.1.0-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 772beef0857f7c620bc2e460be773d31dfa69f312b6bd2fc692b4630b5b8e12e |
|
MD5 | c22b7617397cf4c3e43bfce9189d2b32 |
|
BLAKE2b-256 | 968acde6b81d2ba6badb42fccfc2b845f1a6d35f6d7e3aaba27dc40fbaf07b0a |
Close
Hashes for ngram_lm-0.1.0-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 88746fcb1173c11cbf34edfaa8a7a926e14a95a8ef885691ad666d7661f9d442 |
|
MD5 | 318c70aad3df56bd0d3ce5120b58150f |
|
BLAKE2b-256 | 4c2528702dc8e1df64d58831793a52482653466fdf3c64a7acbbe3e66d846a54 |
Close
Hashes for ngram_lm-0.1.0-cp36-cp36m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | dc19a2c075a3d6c2864c04c4f615425a52ca6979f18bebf1b2c3a88af2e1a7d5 |
|
MD5 | a2a94df788af1b42cea2ba77fc0700b6 |
|
BLAKE2b-256 | fc6fa448b8a54205a10163994ae22dfc0703215cc6fe0ad74b7362c1e29dacb6 |