Bump version to 0.3.2

ZurichNLP · May 30, 2023 · ee2e8ad · ee2e8ad
1 parent 02d56a0
commit ee2e8ad
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 2 deletions.
diff --git a/README.md b/README.md
@@ -159,6 +159,10 @@ See [experiments/README.md](experiments/README.md)
 - Data: See data subdirectories
 
 ## Changelog
+- v0.3.2
+  - Fix score calculation with `small100` model (account for the fact that the target sequence is not prefixed with the target language, as is the case for `m2m100`).
+  - Improve caching efficiency
+
 - v0.3.1
   - Implement the distilled [`small100`](https://huggingface.co/alirezamsh/small100) model by [Mohammadshahi et al. (2022)](https://aclanthology.org/2022.emnlp-main.571/) and use this model by default.
   - Enable half-precision inference for `m2m100` models and `small100` by default; see (/experiments/results/summary.md) for benchmark results

diff --git a/setup.cfg b/setup.cfg
@@ -1,6 +1,6 @@
 [metadata]
 name = nmtscore
-version = 0.3.1
+version = 0.3.2
 author = Jannis Vamvas
 author_email = vamvas@cl.uzh.ch
 description = A library of translation-based text similarity measures

diff --git a/src/nmtscore/__init__.py b/src/nmtscore/__init__.py
@@ -1,3 +1,3 @@
 from nmtscore.scorer import NMTScorer
 
-__version__ = "0.3.1"
+__version__ = "0.3.2"