diff --git a/faster_whisper/transcribe.py b/faster_whisper/transcribe.py
index 3973fe6..80aade4 100644
--- a/faster_whisper/transcribe.py
+++ b/faster_whisper/transcribe.py
@@ -101,8 +101,8 @@ class WhisperModel:
             having multiple workers enables true parallelism when running the model
             (concurrent calls to self.model.generate() will run in parallel).
             This can improve the global throughput at the cost of increased memory usage.
-          download_root: Directory where the model should be saved. If not set, the model
-            is saved in the standard Hugging Face cache directory.
+          download_root: Directory where the models should be saved. If not set, the models
+            are saved in the standard Hugging Face cache directory.
           local_files_only:  If True, avoid downloading the file and return the path to the
             local cached file if it exists.
         """
diff --git a/faster_whisper/utils.py b/faster_whisper/utils.py
index a052ad8..fe56ab9 100644
--- a/faster_whisper/utils.py
+++ b/faster_whisper/utils.py
@@ -45,7 +45,7 @@ def download_model(
       size: Size of the model to download (tiny, tiny.en, base, base.en, small, small.en,
         medium, medium.en, large-v1, or large-v2).
       output_dir: Directory where the model should be saved. If not set, the model is saved in
-        the standard Hugging Face cache directory.
+        the cache directory.
       local_files_only:  If True, avoid downloading the file and return the path to the local
         cached file if it exists.
       cache_dir: Path to the folder where cached files are stored.