cctv?

PiliPala 是使用Flutter开发的BiliBili第三方客户端，感谢使用。

CTC models for keyword spotting

I have tried to figure out a way to run raspberry pi using QEMU but could not. So here I am putting all the references I have pieced together that should just work out of the box.

An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.

Official implementation of the Interspeech 2024 paper "Lightweight Transducer Based on Frame Level Criterion".

List of papers related to Vision Transformers quantization and hardware acceleration in recent AI conferences and journals.

0️⃣1️⃣🤗 BitNet-Transformers: Huggingface Transformers Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch with Llama(2) Architecture

[ICML'21 Oral] I-BERT: Integer-only BERT Quantization

Post-Training Quantization for Vision transformers.

[IJCAI 2022] FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer

The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

模型压缩的小白入门教程

This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.

手搓的llm评测指南

The smallest hardware device for efficient large for efficient language models (LLMs) inference optimized for low-power, low-cost embedded SoCs, supporting on-device real-time Whisper speech-to-tex…

A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).

Greentown Smart Home Command Language Large Model(SmartHomeCLLM), trained from tens of thousands of smart home control commands 智能家居指令大模型，通过数万条智能家居控制指令训练而成的大模型

ncnn vs2015 examples demo

ASiT: Audio Spectrogram vIsion Transformer for General Audio Representation

Kaldi-compatible online fbank extractor without external dependencies

A No-Recurrence Sequence-to-Sequence Model for Speech Recognition

speech enhancement\speech seperation\sound source localization

This repo summarizes the tutorials, datasets, papers, codes and tools for speech separation and speaker extraction task. You are kindly invited to pull requests.

A neural network inference lib implemented with STD C. *Experimental*

中文常用停用词表（哈工大停用词表、百度停用词表等）

高性能并行编程与优化 - 课件