pydub
openai-cookbook
pydub | openai-cookbook | |
---|---|---|
25 | 215 | |
8,355 | 56,065 | |
- | 1.0% | |
0.0 | 9.5 | |
about 1 month ago | 3 days ago | |
Python | MDX | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
pydub
- Looking for help with a winamp project please.
-
Best language(s) for creating/manipulating sounds
Honestly while, C++ is used for professional audio software, you can get a lot done with python and a library like pydub, or you can even learn to manipulate audio files without any libraries in any language. So if you are not particulary interested in C++ at the moment you can start with Python, which is easier to learn. You can check out other python audio manipulation libraries here
-
ChatGPT and Whisper APIs
I doubt it will matter if you're breaking up mid sentence if you pass in the previous as a prompt and split words. This is how Whisper does it internally.
It's not absolutely perfect, but splitting on the word boundary is one line of code with the same package in their docs: https://github.com/jiaaro/pydub/blob/master/API.markdown#sil...
25MB is also a lot. That's 30 minutes to an hour on MP3 at reasonable compression. A 2 hour movie would have three splits.
-
FFmpeg 6.0
Even given an option it can be difficult to find the corresponding documentation, if only because of the many different submodules and encoders and decoders and filters that have o-so-slightly different options. That said, I've just switched from pydub to ffmpeg-python (due to memory issues of the former[1]) and judging from the Jupiter notebook[2] it seems a much more intuitive method of constructing ffmpeg pipelines.
[1] https://github.com/jiaaro/pydub/issues/135
[2] https://github.com/kkroening/ffmpeg-python/tree/master/examp...
-
Download & Trim MP3 from Youtube with Python
With the file downloaded, we're now going to arbitrarily slice it locally (you might have considered wheter it is possible to simply download a clip from youtube; all reliable methods I've found will essentially boil down to downloading the whole and then editing locally). For that we'll use the pydub library:
-
Playing multiple .wav and/or mp3 files in Python
I guess it's possible in theory, a quick search suggest pydub library.But you may find something better if you do a little research.
-
I made a cross-platform command-line app called maestro to play music!
Uses https://github.com/cheofusi/just_playback to play sound. It's actually surprising how hard it was to find a cross-platform Python module to play sound that doesn't require an external dependency like ffmpeg. Even then, modules like https://github.com/jiaaro/pydub don't support features like seeking/scrubbing, which was a must-have for my project.
-
Batch conversion FLAC to WAV
Once python is installed, you will also need to install the "pydub" package for this script to work. If you're on a Windows computer, you can do this from the command line (run the "cmd") program. If you're on mac, you can do this from the terminal. Basically, the way that you do this is using "pip" -- a "helper" program that comes with python. Once you launch the command line, just run the command python -m pip install pydub --upgrade and you should see a message showing that it successfully installed. If you're struggling with this step, just google how to "pip install python packages" and you can find a lot of beginner guides.
-
How can I modify the pitch of an audio file and save it to disk?
That is kinda what serverless functions are built for. Looks like python has some good libraries for this: https://github.com/jiaaro/pydub.
-
Playing large audio files?
The files are big, so it's not feasible to load one in all at once. They have to be streamed/chunked somehow. (sadly, pydub doesn't support this...)
openai-cookbook
-
Question-Answer System Architectures using LLMs
A pretrained LLM is a closed-book system: It can only access information that it was trained on. With domain fine-tuning, the system manifests additional material. An early prototype of this technique was shown in this OpenAi cookbook: For the target domain, text was embedded using an API, and then when using the LLM, embeddings were retrieved using semantic similarity search to formulate an answer. Although this approach evolved to retrieval-augmented generation, its still a technique to adapt a Gen2 (2020) or Gen3 (2022) LLM into a question-answering system.
-
Ask HN: High quality Python scripts or small libraries to learn from
https://github.com/openai/openai-cookbook/blob/main/examples...
- Collection of notebooks showcasing some fun and effective ways of using Claude
- OpenAI Cookbook: Techniques to improve reliability
- OpenAI Cookbooks
-
How to fine tune vit/convnet to focus on the layout of the input room image and ignore other things ?
It sounds like you are trying to tweak embeddings for similarity search. Rather than fine-tune the model's layers, you may want to try training a linear transformation the existing model's output embedding. Openai has a cookbook on how to do that. You will need some data though - but I think you can try it with ~20 pieces of synthetically generated data.
-
Best base model 1B or 7B for full finetuning
tutorial from OpenAI https://github.com/openai/openai-cookbook/blob/main/examples/Question_answering_using_embeddings.ipynb
-
Resources to learn ChatGPT and the OpenAI API
OpenAI Cookbook
- OpenAI Cookbook
-
Another Major Outage Across ChatGPT and API
OpenAI community repo with lots of examples: https://github.com/openai/openai-cookbook
What are some alternatives?
librosa - Python library for audio and music analysis
langchain - ⚡ Building applications with LLMs through composability ⚡ [Moved to: https://github.com/langchain-ai/langchain]
SpeechRecognition - Speech recognition module for Python, supporting several engines and APIs, online and offline.
gpt4-pdf-chatbot-langchain - GPT4 & LangChain Chatbot for large PDF docs
pyAudioAnalysis - Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications
chatgpt-retrieval-plugin - The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.
ffmpeg-python - Python bindings for FFmpeg - with complex filtering support
askai - Command Line Interface for OpenAi ChatGPT
mutagen - Python module for handling audio metadata
gpt_index - LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data. [Moved to: https://github.com/jerryjliu/llama_index]
audioread - cross-library (GStreamer + Core Audio + MAD + FFmpeg) audio decoding for Python
txtai - 💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows