Search for a command to run...
I’m a backend developer based in Beijing, passionate about crafting efficient and scalable solutions. Amidst my coding endeavors, I’ve embarked on an exciting journey as an active English learner. Exploring the intricacies of language allows me to broaden my horizons and connect with diverse communities worldwide. Join me as I navigate the realms of technology and language, striving for excellence in both.
No comments yet. Be the first to comment.
Introduction As you know, Ollama is a very easy-to-use tool for local LLM. It lets people run and experience the latest models with little effort, using simple commands such as: ollama run llama3 ollama ps / ollama list ollama serve What's more ...
Background I am using a QNAP ARM CPU NAS, so its power efficiency is supposed to be a great advantage. I want to integrate the accessories, especially the IR remote, with HomeKit for a better user experience when controlling the old air conditioner...
#include <future> #include <iostream> #include <thread> int main() { // future from a packaged_task std::packaged_task<int()> task([]{ return 7; }); // wrap the function std::future<int> f1 = task.get_future(); // get a future std::t...
Q & A CLANG basic setting Break point is not accurate optimize_list = [ "-O0", "-g", ] Envs export CXX=clang compile_flags.txt # Treat all files as C++ files -xc++ -std=c++17 BUILD If use blade, the generated build command with CLANG will in...
Introduction As you know, Ollama is a very easy-to-use tool for local LLM. It lets people run and experience the latest models with little effort, using simple commands such as: ollama run llama3 ollama ps / ollama list ollama serve What's more ...
Recently, I attended a training session where the host used many filler words and repeated examples, causing it to last longer than it should have. Fortunately, I recorded the video using the Tencent Meeting software. I had an idea to extract the audio from this video clip (since there is barely any video movement during the session), then convert the audio to text, and finally, let GPT-4 summarize it for me.
My solution seems clear: use FFMPEG (for video extraction), ASR (to recognize the voice), and ChatGPT (preferably GPT-4-16k, as the text is usually too long for the standard GPT-4 model).
There are two purposes for using ffmpeg here:
ffmpeg can extract the video clip to a pure audio file.
ffmpeg can convert the existing audio file to a harmless format like wav, which is required by most ASR models. However, you should know that ffmpeg cannot improve the audio file quality, such as bitrate (which is common knowledge).
Installation is very easy if you use the right software management tools.
brew install ffmpeg
Use the command with a small modification (change input.mp4/output.wav):
ffmpeg -i input.mp4 -acodec pcm_s16le -ac 2 -ar 16000 output.wav
Actually, we are using the whisper-cpp, a high-performance version of OpenAI's Whisper automatic speech recognition (ASR) model. The most important feature is that it includes some pre-trained models under the Apple ML standard, which can fully utilize the powerful NPU in Apple Silicon.
Installation
# Installation of whisper is not necessary, however, it helps you preinstall a lot of stuff
brew install whisper
brew install whisper-cpp
# Set this path, and the subdirectory models will be used to store all models.
export GGML_METAL_PATH_RESOURCES=/opt/homebrew/share/whisper-cpp
Finally, you can check this page to manually download the appropriate model for yourself. I prefer the small model, which is totally fine. After that, you can use the command whisper-cpp freely to recognize any text you want.
The basic command is shown below, and you can specify the language using the -l option.
-m specify the model.
-otxt output filename with a .txt extension; it can support multiple output formats.
whisper-cpp -m ./models/ggml-small.bin ~/Downloads/audio.wav -l zh -otxt hello.txt
I don't think it's necessary to include this part here because there are many similar blogs, whether using GPT-4, Copilot, or APIs (provided by Microsoft Azure or OpenAI). The main thing you should focus on is using the 16K model. This is because meeting transcripts are usually very long, and the standard GPT-4 model can't handle them effectively.
Have fun! I believe it's a better way to save your time from long and boring meetings.