Code required to train spaCy-compatible sentence segmenter for Latin.
The project.yml
defines the data assets required by the
project, as well as the available commands and workflows. For details, see the
spaCy projects documentation.
The following commands are defined by the project. They
can be executed using spacy project run [name]
.
Commands are only re-run if their inputs have changed.
Command | Description |
---|---|
assets |
Download assets |
preprocess |
Convert the data to spaCy's format |
load-vectors |
load floret vectors |
train |
Train senter |
evaluate |
Evaluate on the test data and save the metrics |
package |
Package the trained model so it can be installed |
document |
Document senter |
clean |
Remove intermediate files |
The following workflows are defined by the project. They
can be executed using spacy project run [name]
and will run the specified commands in order. Commands are only re-run if their
inputs have changed.
Workflow | Steps |
---|---|
all |
assets β preprocess β load-vectors β train β evaluate β package β document β clean |
The following assets are defined by the project. They can
be fetched by running spacy project assets
in the project directory.
File | Source | Description |
---|---|---|
assets/treebanks/UD_Latin-Perseus |
Git | |
assets/treebanks/UD_Latin-PROIEL |
Git | |
assets/treebanks/UD_Latin-ITTB |
Git | |
assets/treebanks/UD_Latin-LLCT |
Git | |
assets/treebanks/UD_Latin-UDante |
Git |
- To install the current version...
pip install https://huggingface.co/diyclassics/la_senter/resolve/main/la_senter-0.3.0/dist/la_senter-0.3.0.tar.gz
Feature | Description |
---|---|
Name | la_senter |
Version | 0.3.0 |
spaCy | >=3.4.2,<3.6.0 |
Default Pipeline | senter |
Components | senter |
Vectors | -1 keys, 50000 unique vectors (300 dimensions) |
Sources | UD_Latin-Perseus UD_Latin-PROIEL UD_Latin-ITTB UD_Latin-LLCT UD_Latin-UDante |
License | MIT |
Author | Patrick J. Burns |
Type | Score |
---|---|
SENTS_F |
99.55 |
SENTS_P |
99.45 |
SENTS_R |
99.65 |
SENTER_LOSS |
4029.93 |