MicBot - MicBot uses Google Translate to speak everyone's chat messages

Related tags

Text Data & NLPMicBot
Overview

MicBot

MicBot uses Google Translate to speak everyone's chat messages. It can also play audio from youtube links sent via chat. You'll need to setup a spare PC or VM for the sole purpose of running this bot. The server you join must also have the MicBot plugin installed (this probably won't be a requirement in the future).

Say .mhelp for usage on servers which have the MicBot plugin installed.

MicBot reads messages aloud and can play audio from youtube links.
    ~<message> = Hide your message from the chat.
    .mpitch <1-200>   = set text-to-speech pitch.
    .mlang <language> = set text-to-speech language.
    .mlangs           = list valid languages.
    .mstop            = Stop all audio.
    .mstop speak      = Stop all text-to-speech audio.
    .mstop last       = Stop all youtube videos except the one that first started playing.
    .mstop first      = Stop all youtube videos except the one that last started playing.
    .mtts             = enable/disable text to speech for your messages.
    .mbot             = register/unregister yourself as a bot with the server.

    You can add a timestamp after a youtube link to play at an offset. For example:
    https://www.youtube.com/watch?v=b8HO6hba9ZE 0:27

Windows installation:

  1. Install Python 3
  2. pip install pafy gtts python-vlc pyglet pynput pydub youtube_dl yt-dlp pynput
    • If yt-dlp fails to install, then try this command: pip install --no-deps -U yt-dlp
    • You might need to install some .NET framework or visual studio stuff. Any error messages you see should be google-able.
  3. Install the appropriate version of VLC (64-bit VLC if you got 64-bit python. 32-bit VLC if 32-bit python.)
  4. Install ffmpeg and add the /bin folder to your system PATH (environment variable).
  5. Make "Stereo mix" your default recording device for sven or install something like Virtual Audio Cable to get sven to hear your desktop sounds.

Linux installation:

  1. sudo apt install xdotool python3-gst-1.0 python3 python3-pip ffmpeg vlc
  2. pip3 install pafy gtts python-vlc pyglet pydub youtube_dl yt-dlp
  3. Redirect sven to record from your speaker output. I had to do this for a Lubuntu 18.04 x64 VM:
    • sudo apt install pavucontrol
    • pactl load-module module-loopback latency_msec=1
    • Set sound card profile to "Off" in Configuration tab of the volume settings (this will disable speakers but I wanted that anyway)

Final installation steps

  1. Edit backend_youtube_dl.py in the pafy python library (default windows path: Python3x/Lib/site-packages/pafy/):
    • comment out the lines that have like_count and dislike_count. As of this writing, the current version of pafy will fail to fetch youtube links because of the removal of likes/dislikes from YouTube.
    • [Optional] If you get "Sign in to verify your age" errors for some videos, then also replace youtube_dl import with import yt_dlp as youtube_dl. This may result in other errors or videos not playing though, so maybe try without doing this first.
  • [Optional] The bot will speak chat sounds by default. If you don't want that, create a file called chatsounds.txt next to the script. Each line should contain a single word which the bot will not speak by itself.

Usage:

  1. Add -condebug to the launch options of Sven Co-op. Then, start the game.
  2. Type in console: volume 0; mp3volume 0; bind F8 "+voicerecord;-voicerecord;+voicerecord"
  3. Join a server which has the MicBot plugin installed.
  4. Say .mbot to register yourself as a bot.
  5. Start the client.py script
  6. Keep the game in focus and without the menu/console showing. The script will continue pressing F8 to keep the mic enabled across level changes.
Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention

Sinkhorn Transformer This is a reproduction of the work outlined in Sparse Sinkhorn Attention, with additional enhancements. It includes a parameteriz

Phil Wang 217 Nov 25, 2022
A curated list of efficient attention modules

awesome-fast-attention A curated list of efficient attention modules

Sepehr Sameni 891 Dec 22, 2022
A simple implementation of N-gram language model.

About A simple implementation of N-gram language model. Requirements numpy Data preparation Corpus Training data for the N-gram model, a text file lik

4 Nov 24, 2021
A simple Flask site that allows users to create, update, and delete posts in a database, as well as perform basic NLP tasks on the posts.

A simple Flask site that allows users to create, update, and delete posts in a database, as well as perform basic NLP tasks on the posts.

Ian 1 Jan 15, 2022
The Internet Archive Research Assistant - Daily search Internet Archive for new items matching your keywords

The Internet Archive Research Assistant - Daily search Internet Archive for new items matching your keywords

Kay Savetz 60 Dec 25, 2022
Official PyTorch implementation of SegFormer

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers Figure 1: Performance of SegFormer-B0 to SegFormer-B5. Project page

NVIDIA Research Projects 1.4k Dec 29, 2022
Associated Repository for "Translation between Molecules and Natural Language"

MolT5: Translation between Molecules and Natural Language Associated repository for "Translation between Molecules and Natural Language". Table of Con

67 Dec 15, 2022
Mysticbbs-rjam - rJAM splitscreen message reader for MysticBBS A46+

rJAM splitscreen message reader for MysticBBS A46+

Robbert Langezaal 4 Nov 22, 2022
Code for CodeT5: a new code-aware pre-trained encoder-decoder model.

CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation This is the official PyTorch implementation

Salesforce 564 Jan 08, 2023
code for modular summarization work published in ACL2021 by Krishna et al

This repository contains the code for running modular summarization pipelines as described in the publication Krishna K, Khosla K, Bigham J, Lipton ZC

Approximately Correct Machine Intelligence (ACMI) Lab 21 Nov 24, 2022
The PyTorch based implementation of continuous integrate-and-fire (CIF) module.

CIF-PyTorch This is a PyTorch based implementation of continuous integrate-and-fire (CIF) module for end-to-end (E2E) automatic speech recognition (AS

Minglun Han 24 Dec 29, 2022
An easy-to-use framework for BERT models, with trainers, various NLP tasks and detailed annonations

FantasyBert English | 中文 Introduction An easy-to-use framework for BERT models, with trainers, various NLP tasks and detailed annonations. You can imp

Fan 137 Oct 26, 2022
Machine translation models released by the Gourmet project

Gourmet Models Overview The Gourmet project has released several machine translation models to translate low-resource languages. This repository conta

Edinburgh NLP 5 Dec 08, 2021
A design of MIDI language for music generation task, specifically for Natural Language Processing (NLP) models.

MIDI Language Introduction Reference Paper: Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions: code This

Robert Bogan Kang 3 May 25, 2022
Python package for Turkish Language.

PyTurkce Python package for Turkish Language. Documentation: https://pyturkce.readthedocs.io. Installation pip install pyturkce Usage from pyturkce im

Mert Cobanov 14 Oct 09, 2022
🌸 fastText + Bloom embeddings for compact, full-coverage vectors with spaCy

floret: fastText + Bloom embeddings for compact, full-coverage vectors with spaCy floret is an extended version of fastText that can produce word repr

Explosion 222 Dec 16, 2022
Original implementation of the pooling method introduced in "Speaker embeddings by modeling channel-wise correlations"

Speaker-Embeddings-Correlation-Pooling This is the original implementation of the pooling method introduced in "Speaker embeddings by modeling channel

Themos Stafylakis 10 Apr 30, 2022
Yodatranslator is a simple translator English to Yoda-language

yodatranslator Overview yodatranslator is a simple translator English to Yoda-language. Project is created for educational purposes. It is intended to

1 Nov 11, 2021
超轻量级bert的pytorch版本,大量中文注释,容易修改结构,持续更新

bert4pytorch 2021年8月27更新: 感谢大家的star,最近有小伙伴反映了一些小的bug,我也注意到了,奈何这个月工作上实在太忙,更新不及时,大约会在9月中旬集中更新一个只需要pip一下就完全可用的版本,然后会新添加一些关键注释。 再增加对抗训练的内容,更新一个完整的finetune

muqiu 317 Dec 18, 2022
Utilities for preprocessing text for deep learning with Keras

Note: This utility is really old and is no longer maintained. You should use keras.layers.TextVectorization instead of this. Utilities for pre-process

Hamel Husain 180 Dec 09, 2022