Stars
PEFT-SER: On the Use of Parameter Efficient Transfer Learning Approaches For Speech Emotion Recognition Using Pre-trained Speech Models (Accepted to 2023 ACII)
Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.
Self-Supervised Speech Pre-training and Representation Learning Toolkit
Codebase for the paper 'EncodecMAE: Leveraging neural codecs for universal audio representation learning'
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.
Rembg is a tool to remove images background
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
ImageBind One Embedding Space to Bind Them All
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
Scraping publicly-accessible Letterboxd data and creating a movie recommendation model with it that can generate recommendations when provided with a Letterboxd username
A playbook for systematically maximizing the performance of deep learning models.
Rapid fuzzy string matching in Python using various string metrics
Robust Speech Recognition via Large-Scale Weak Supervision
📺 Discover the latest machine learning / AI courses on YouTube.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
Python library for converting Python calculations into rendered latex.