unbabel-comet

library2.2.7pypypi✓ verified 85d ago

High-quality Machine Translation Evaluation library using neural models. Version 2.2.7. Active development on GitHub, with minor releases every few months.

ai-ml llm-agents

pip install unbabel-comet

github ↗package ↗docs ↗

INSTALL

IMPORT

SIG · UNBABEL-COMET

unbabel-comet

ai-mlpythonv2.2.7

harness data pending

Install & Compatibility

Where this runs

No compatibility data collected yet for this library.

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

download_model

✓ from comet import download_model

✗ from comet.models import download_model

download_model is at the package level, not in comet.models

load_from_checkpoint

✓ from comet import load_from_checkpoint

✗ from comet.models import load_from_checkpoint

Same as download_model; package-level function

Load a COMET model and score translation pairs.

from comet import download_model, load_from_checkpoint model_path = download_model("Unbabel/wmt22-comet-da") model = load_from_checkpoint(model_path) data = [ { "src": "This is a source sentence.", "mt": "Ceci est une phrase source.", "ref": "This is a reference translation." } ] seg_scores, sys_score = model.predict(data, batch_size=8, gpus=1) print(seg_scores, sys_score)

comet --version

Debug

Known issues

gotchaThe `predict` method expects a list of dicts with keys 'src', 'mt', and optionally 'ref'. Missing keys cause KeyError.

fix

Ensure each dict contains 'src' and 'mt' keys (and 'ref' if required).

affects: all

gotchaModel downloads can be large (several GB). The download_model function caches in ~/.cache/comet by default.

fix

Set environment variable COMET_CACHE_DIR to a custom path.

affects: all

deprecatedThe `comet-score` CLI uses model.half() by default starting v2.2.5, which slightly changes scores compared to v2.2.4.

fix

Upgrade to v2.2.6+ for consistent half-precision behavior.

affects: >=2.2.5, <2.2.6

gotchaSome models (like XCOMET) are only for inference and not for training in current releases.

fix

Check model documentation to confirm training support.

affects: >=2.2.0, <2.3.0

Errors

Common errors & fixes

KeyError: 'src'

Missing required key in input data dict.

fix

Ensure each sample dict has 'src' and 'mt' keys.

requests.exceptions.ConnectionError: HTTPConnectionPool

Network issue downloading model from Hugging Face hub.

fix

Check internet connection or set HF_HUB_OFFLINE=1 to use cached models.

AttributeError: module 'comet' has no attribute 'download_model'

Incorrect import path.

fix

Use 'from comet import download_model' instead of 'from comet.models import download_model'.

Upgrade

Version history

2.2.7latest on PyPI · released Sep 1, 2025

Audit

Dependencies

torchrequiredRequired for model inference

Agent activity

39 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/Unbabel/COMET ↗

packagehttps://pypi.org/project/unbabel-comet/ ↗

docshttps://unbabel.github.io/COMET/html/index.html ↗