# Speech Language Model

This is the result of weighted/importance matrix quantization of the Menlo/Speechless-llama3.2-v0.1 model, offering multiple quantization versions

A high-quality speech language model trained on a single GPU within 24 hours, fine-tuned based on Qwen2.5-0.5B, using Hubert tokens as vocabulary

This is a speech language model based on discrete Hubert tokens, focusing on efficient training and capable of generating speech segment continuations.

SpeechGPT is a large language model with intrinsic cross-modal dialogue capabilities, capable of perceiving and generating multimodal content, supporting interaction via speech and text.

SpeechGPT is a large language model with intrinsic cross-modal dialogue capabilities, capable of perceiving and generating multimodal content based on human instructions.