pylSER
Follow
Stars
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
The simplest, fastest repository for training/finetuning medium-sized GPTs.
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
verl: Volcano Engine Reinforcement Learning for LLMs
Development repository for the Triton language and compiler
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
Self-Supervised Speech Pre-training and Representation Learning Toolkit
A high-throughput and memory-efficient inference and serving engine for LLMs
Voice activity detection (VAD) paper and code（From 198*~ ）and its classification.
Keep track of big models in audio domain, including speech, singing, music etc.
Paper, Code and Statistics for Self-Supervised Learning and Pre-Training on Speech.
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
deepspeedai / Megatron-DeepSpeed
Forked from NVIDIA/Megatron-LMOngoing research training transformer language models at scale, including: BERT & GPT-2
Robust Speech Recognition via Large-Scale Weak Supervision
Stable diffusion for real-time music generation
Stable diffusion for real-time music generation (web app)
Tools to train a generative model on arbitrary audio samples
List of academic resources on Multimodal ML for Music
kaldi-asr/kaldi is the official location of the Kaldi project.
the clustering model and the method of disease early-warning detection based on differential distribution
Production First and Production Ready End-to-End Speech Recognition Toolkit
💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.