From e6909bf4a5885eee90f730d1fadf98417079d525 Mon Sep 17 00:00:00 2001 From: mhubii Date: Mon, 25 Nov 2024 11:35:44 +0000 Subject: [PATCH] moved example to top --- README.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index 3866bdd..63033ef 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,12 @@ # ROS 2 Whisper ROS 2 inference for [whisper.cpp](https://github.com/ggerganov/whisper.cpp). +## Example + +This example shows live transcription of first minute of the 6'th chapter in ***Harry Potter and the Philosopher's Stone*** from Audible: + +![harry_potter_sample](./doc/harry_potter_sample.gif) + ## Build - Install `pyaudio`, see [install instructions](https://pypi.org/project/PyAudio/). - Build this repository, do @@ -64,12 +70,6 @@ Topics of type [AudioTranscript.msg](whisper_idl/msg/AudioTranscript.msg) on `/w Internally, the topic `/whisper/tokens` of type [WhisperTokens.msg](whisper_idl/msg/WhisperTokens.msg) is used to transfer the model output between nodes. -## Example - -This example shows live transcription of first minute of the 6'th chapter in ***Harry Potter and the Philosopher's Stone*** from Audible: - -![harry_potter_sample](./doc/harry_potter_sample.gif) - ## Troubleshoot - Encoder inference time: https://github.com/ggerganov/whisper.cpp/issues/10#issuecomment-1302462960