diff options
author | ZJaume <jzaragoza@prompsit.com> | 2022-07-27 14:12:23 +0300 |
---|---|---|
committer | ZJaume <jzaragoza@prompsit.com> | 2022-07-27 14:13:07 +0300 |
commit | 66001fb7156999c8313855b2fabfd1259355b78a (patch) | |
tree | 97d387fbba6a784473f40ba64a9c463220f7df99 | |
parent | a5f8499287e38b1852a38d850c85f05ff7276d97 (diff) |
Update hardrules and installation instructions
-rw-r--r-- | README.md | 17 | ||||
-rw-r--r-- | requirements.txt | 2 |
2 files changed, 5 insertions, 14 deletions
@@ -47,21 +47,12 @@ The use of XLMRoberta and 1:10 positive to negative ratio were inspired in the w - TensorFlow >= 2.6.5 - CUDA 11.2 (for training and inference with full models) -Bicleaner AI is written in Python and can be installed using `pip`: +Bicleaner AI is written in Python and can be installed using `pip`. +It also requires the [KenLM](https://github.com/kpu/kenlm) Python bindings with support for 7-gram language models. +You can easily install it by running the following command: ```bash -pip install bicleaner-ai -``` - -Bicleaner AI requires the [KenLM](https://github.com/kpu/kenlm) Python bindings with support for 7-gram language models. You can easily install it by running the following commands: - -```bash -git clone https://github.com/kpu/kenlm -cd kenlm -pip install . --install-option="--max_order 7" -mkdir -p build && cd build -cmake .. -DKENLM_MAX_ORDER=7 -DCMAKE_INSTALL_PREFIX:PATH=/your/prefix/path -make -j all install +pip install bicleaner-ai https://github.com/kpu/kenlm/archive/master.zip --install-option="--max_order 7" ``` Hardrules uses [FastSpell](https://github.com/mbanon/fastspell) that requires `python-dev` and `libhunspell-dev`: diff --git a/requirements.txt b/requirements.txt index 1d07d4b..8373732 100644 --- a/requirements.txt +++ b/requirements.txt @@ -5,7 +5,7 @@ pytest toolwrapper joblib sacremoses -bicleaner-hardrules>=2.1 +bicleaner-hardrules>=2.3,<3.0 sentencepiece tensorflow>=2.6.5 glove-python-binary==0.2.0 |