Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Upgrade eflomal #433

Merged
merged 6 commits into from
Jul 8, 2024
Merged

Upgrade eflomal #433

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
3bce65a
update eflomal to 2.0.0
mshannon-sil Jul 2, 2024
913f9c3
set up eflomal in Dockerfile; add eflomal to aligners dictionary
mshannon-sil Jul 2, 2024
044ac9e
update EFLOMAL_PATH in Dockerfile
mshannon-sil Jul 2, 2024
949dd42
remove eflomal from ALIGNERS by default
mshannon-sil Jul 2, 2024
62a4d84
Move eflomal checks inside of eflomal.py
isaac091 Jul 2, 2024
a1955a7
Merge pull request #436 from sillsdev/eflomal_warning
mshannon-sil Jul 3, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 3 additions & 6 deletions Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,7 @@ RUN apt-get install --no-install-recommends -y \
git \
python$PYTHON_VERSION \
python3-pip \
python3-dev \
wget \
build-essential \
gdb \
Expand All @@ -59,12 +60,8 @@ RUN ln -sfn /usr/bin/python${PYTHON_VERSION} /usr/bin/python3 & \
COPY --from=builder /src/requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt && rm requirements.txt

# Install eflomal
RUN git clone https://github.com/robertostling/eflomal.git
RUN make -C eflomal/src
RUN make -C eflomal/src install
RUN rm -rf eflomal
ENV EFLOMAL_PATH=/usr/local/bin
# Set eflomal path
ENV EFLOMAL_PATH=/usr/local/lib/python3.8/dist-packages/eflomal/bin

# Install fast_align
RUN apt-get update && \
Expand Down
11 changes: 6 additions & 5 deletions poetry.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@ sacremoses = "^0.0.53"
evaluate = "^0.3.0"
python-docx = "^0.8.11"
iso639-lang = "^2.1.0"
eflomal = { version = "^0.1", optional = true }
eflomal = { version = "^2.0.0", optional = true }
accelerate = "^0.23.0"
transformers = "^4.36.2"
optimum = "^1.16.0"
Expand Down
10 changes: 2 additions & 8 deletions silnlp/alignment/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,6 @@
from ..common.environment import SIL_NLP_ENV
from ..common.flatcat_stemmer import FlatCatStemmer
from ..common.null_stemmer import NullStemmer
from ..common.packages_utils import is_eflomal_available
from ..common.snowball_stemmer import SnowballStemmer
from ..common.stemmer import Stemmer
from ..common.utils import merge_dict
Expand All @@ -24,10 +23,7 @@
Ibm4DotnetMachineAligner,
ParatextDotnetMachineAligner,
)

if is_eflomal_available():
from .eflomal import EflomalAligner

from .eflomal import EflomalAligner
from .fast_align import FastAlign
from .giza_aligner import HmmGizaAligner, Ibm1GizaAligner, Ibm2GizaAligner, Ibm3GizaAligner, Ibm4GizaAligner
from .machine_aligner import (
Expand Down Expand Up @@ -67,11 +63,9 @@
"clear3_fa": (ClearAligner, "Clear-3-FA"),
"clear3_hmm": (ClearAligner, "Clear-3-HMM"),
"clab_fast_align": (FastAlign, "clab-FastAlign"),
"eflomal": (EflomalAligner, "Eflomal"),
}

if is_eflomal_available():
ALIGNERS["eflomal"] = (EflomalAligner, "Eflomal")

STEMMERS: Dict[str, Type[Stemmer]] = {
"snowball": SnowballStemmer,
"wordnet": WordNetStemmer,
Expand Down
8 changes: 7 additions & 1 deletion silnlp/alignment/eflomal.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,20 +6,26 @@
from tempfile import TemporaryDirectory
from typing import IO, Iterable

from eflomal import read_text, write_text
from machine.corpora import AlignedWordPair
from machine.translation import SymmetrizationHeuristic, WordAlignmentMatrix

from ..common.corpus import load_corpus
from ..common.packages_utils import is_eflomal_available
from .aligner import Aligner
from .lexicon import Lexicon
from .tools import execute_atools, execute_eflomal, is_atools_available

if is_eflomal_available():
from eflomal import read_text, write_text

LOGGER = logging.getLogger(__name__)


class EflomalAligner(Aligner):
def __init__(self, model_dir: Path) -> None:
if not is_eflomal_available():
raise RuntimeError("eflomal is not installed.")

super().__init__("eflomal", model_dir)

def train(self, src_file_path: Path, trg_file_path: Path) -> None:
Expand Down