diff --git a/README.md b/README.md
index 83f30cbc..0298818c 100644
--- a/README.md
+++ b/README.md
@@ -386,7 +386,7 @@ Run the inference examples as usual, for example:
 ## Moore Threads GPU support
 
 With Moore Threads cards the processing of the models is done efficiently on the GPU via muBLAS and custom MUSA kernels.
-First, make sure you have installed `MUSA SDK rc4.0.1`: https://developer.mthreads.com/sdk/download/musa?equipment=&os=&driverVersion=&version=rc4.0.1
+First, make sure you have installed `MUSA SDK rc4.0.1`: https://developer.mthreads.com/sdk/download/musa?equipment=&os=&driverVersion=&version=4.0.1
 
 Now build `whisper.cpp` with MUSA support:
 
diff --git a/tests/librispeech/README.md b/tests/librispeech/README.md
index 85478a0f..670f39b4 100644
--- a/tests/librispeech/README.md
+++ b/tests/librispeech/README.md
@@ -48,7 +48,7 @@ performance of whisper.cpp on LibriSpeech corpus.
 
 ## How-to guides
 
-### How to change the inferece parameters
+### How to change the inference parameters
 
 Create `eval.conf` and override variables.