Stars
The official implementation of HierSpeech++
Accessible large language models via k-bit quantization for PyTorch.
🔊 Text-Prompted Generative Audio Model
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
Code and documentation to train Stanford's Alpaca models, and generate the data.
Denoising Diffusion Probabilistic Models
Production First and Production Ready End-to-End Speech Recognition Toolkit