Code for the paper Hybrid Spectrogram and Waveform Source Separation

Whisper realtime streaming for long speech-to-text transcription and translation

RWKV in nanoGPT style

My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT p…

(Unofficial) Implementation of dilated attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens" (https://arxiv.org/abs/2307.02486)

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

🔊 Text-prompted Generative Audio Model - With the ability to clone voices

Korean Parallel Corpus

RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, …

Custom fork for Bolt EV