diff --git a/README.md b/README.md
index 6e627cd49bb2193e0e1b5272db1e3fbceaf8e8d5..9d1d5f068923b1a181b1ca558b1032d23ee83a5c 100644
--- a/README.md
+++ b/README.md
@@ -50,9 +50,6 @@
GPU execution requires the NVIDIA libraries cuBLAS 11.x and cuDNN 8.x to be installed on the system. Please refer to the [CTranslate2 documentation](https://opennmt.net/CTranslate2/installation.html). This repository demonstrates how to implement the Whisper transcription using [CTranslate2](https://github.com/OpenNMT/CTranslate2/), which is a fast inference engine for Transformer models.-This repository demonstrates how to implement the Whisper transcription using [CTranslate2](https://github.com/OpenNMT/CTranslate2/), which is a fast inference engine for Transformer models.--This repository demonstrates how to implement the Whisper transcription using [CTranslate2](https://github.com/OpenNMT/CTranslate2/), which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than [openai/whisper](https://github.com/openai/whisper) for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU. ### Model conversion
diff --git a/requirements.txt b/requirements.txt
index 8b6def3b29246d58b421c2a05adb59b52497a39a..160f19d6bd170b5d3c635cdbb805d39a694a52bc 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,3 +1,3 @@
av==10.*-ctranslate2>=3.5.1,<4+ctranslate2>=3.6,<4 tokenizers==0.13.*
