-
My North
- Lisbon
Highlights
- Pro
Lists (1)
Sort Name ascending (A-Z)
Stars
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…
[NeurIPS 2023] This is the code for the paper `Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias`.
Tutorials on getting started with PyTorch and TorchText for sentiment analysis.
An extremely fast Python package and project manager, written in Rust.
whisper-cpp-serve Real-time speech recognition and c+ of OpenAI's Whisper model in C/C++
The open-source iOS app that's making quality voice transcription more accessible on mobile devices.
Whisper realtime streaming for long speech-to-text transcription and translation
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with LlamaIndex, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Synthetic data augmentation technique via LLM for Automatic Speech Recognition fine tuning.
Flutter App That Can Transcribe Audio Offline/On Device with Whisper C++ Bindings via Rust
Minimal extension of OpenAI's Whisper adding speaker diarization with special tokens
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
Port of OpenAI's Whisper model in C/C++
Collection of Jupyter Notebooks about Python programming
PyTorch Tutorials from my YouTube channel
Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.
Using deep learning to generate music in MIDI format.
Fine-tune ChatGPT to write lyrics of your favorite artist
Python library to download YouTube content and retrieve metadata
Utilising the concepts of LLM from Langchain and integrating Hugging Face model and Google Gemini AI chatbot to understand emotional sentiments of lyrics and develop a pesudo-RAG that will return q…
Lyrics generation with GPT2-based Transformer
This project uses LLMs to generate music from text by understanding prompts, creating lyrics, determining genre, and composing melodies. It harnesses LLM capabilities to create songs based on text …
Implementation of Lyre-LM: finetuning LLMs for lyric generation (llama-2-7b).