alex-songs Goto Github PK

asr-rescoring

audiolm-pytorch

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

auditok

An audio/acoustic activity detection and audio segmentation tool

awesome-diarization

A curated list of awesome Speaker Diarization papers, libraries, datasets, and other resources.

awesome-llm

Awesome-LLM: a curated list of Large Language Model

bark

🔊 Text-Prompted Generative Audio Model

belle

BELLE: Bloom-Enhanced Large Language model Engine（开源中文对话大模型-70亿参数）

chatllama

ChatLLaMA 📢 Open source implementation for LLaMA-based ChatGPT runnable in a single GPU. 15x faster training process than ChatGPT

chinese-llama-alpaca

中文LLaMA&Alpaca大语言模型+本地部署 (Chinese LLaMA & Alpaca LLMs)

chinese_text_normalization

Chinese text normalization for speech processing

cmsis-dsp

CMSIS-DSP embedded compute library for Cortex-M and Cortex-A

dpsl-asr

Dual-Path Style Learning for End-to-End Noise-Robust Automatic Speech Recognition (DPSL-ASR).

efficientconformer

Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition

espnet

End-to-End Speech Processing Toolkit

faster-whisper

Faster Whisper transcription with CTranslate2

flops-counter.pytorch

Flops counter for convolutional networks in pytorch framework

from_video_get_asr_traindata

这个工程的目的是从视频中获取语音识别的训练数据，用于训练字幕自动生成

git-tips

:trollface:Git的奇技淫巧

gpt4all

gpt4all: a chatbot trained on a massive collection of clean assistant data including code, stories and dialogue

gpt_academic

为GPT/GLM提供图形交互界面，特别优化论文阅读润色体验，模块化设计支持自定义快捷按钮&函数插件，支持代码块表格显示，Tex公式双显示，新增Python和C++项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持清华chatglm等本地模型。兼容复旦MOSS, llama, rwkv, 盘古等。

inferllm

a lightweight LLM model inference framework

instock

InStock股票系统，基于akshare抓取股票每日关键数据，计算股票各种指标，识别K线各种形态，内置多种选股策略，支持选股验证回测，是量化投资工具。Stock system, based on akshare, captures key daily data of stocks, calculates various stock indicators, K-line pattern recognition, has a variety of built-in stock selection strategies, and supports stock selection verification back test. quantitative investment tool.

large-audio-models

Keep track of big models in audio domain, including speech, singing, music etc.

llama

Inference code for LLaMA models

llama-adapter

LLaMA-Adapter: Tuning LLaMa within One Hour and 8M Parameters

llama.cpp

Port of Facebook's LLaMA model in C/C++

llmspracticalguide

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

muavic

MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation

openchatkit

pits

PITS: Variational Pitch Inference for End-to-end Pitch-controllable TTS without External Pitch Predictor