diff --git a/.github/workflows/python-package-pip.yaml b/.github/workflows/python-package-pip.yaml
index 44afad2..e6b6ba8 100644
--- a/.github/workflows/python-package-pip.yaml
+++ b/.github/workflows/python-package-pip.yaml
@@ -10,7 +10,7 @@ on:
 
 env:
   CACHE_NUMBER: 0  # increase to reset cache manually
-  TMPDIR: '/tmp'
+  AAC_METRICS_TMP_PATH: '/tmp'
 
 # Cancel workflow if a new push occurs
 concurrency:
diff --git a/CHANGELOG.md b/CHANGELOG.md
index ddb3470..7cf786a 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -5,8 +5,8 @@ All notable changes to this project will be documented in this file.
 ## [0.5.0] UNRELEASED
 ### Added
 - New `Vocab` metric to compute vocabulary size and vocabulary ratio.
-- New `BERTScoreMRefs` metric to compute BERTScore with multiple references.
-  
+- New `BERTScoreMRefs` metric wrapper to compute BERTScore with multiple references.
+
 ### Changed
 - Rename metric `FluErr` to `FER`.
 
diff --git a/README.md b/README.md
index 347d84d..2600f19 100644
--- a/README.md
+++ b/README.md
@@ -32,6 +32,7 @@ Metrics for evaluating Automated Audio Captioning systems, designed for PyTorch.
     - FER [[9]](#fense)
     - FENSE [[9]](#fense)
     - SPIDEr-FL [[10]](#spider-fl)
+    - Vocab
 
 ## Installation
 Install the pip package: