Maix Speech AI lib, including ASR, chat, TTS etc.

Last update: Dec 25, 2022

Related tags

Text Data & NLP Maix-Speech

Overview

Maix-Speech

中文 | English

Brief

Now only support Chinese, See 中文

Build

Clone code by:

git clone https://github.com/sipeed/Maix-Speech

Compile

x86x64

cd projects/asr

python project.py clean_conf
python project.py menuconfig

python project.py build
# python project.py build --verbose

./build/asr

python project.py clean
python project.py distclean
# python project.py clean_conf

R329

cd projects/asr
python project.py --toolchain /opt/toolchain/bin --toolchain-prefix aarch64-openwrt-linux- config
python project.py menuconfig
python project.py build

More project structure usage

See github.com/Neutree/c_cpp_project_framework

License

Apache 2.0

A fast Text-to-Speech (TTS) model. Work well for English, Mandarin/Chinese, Japanese, Korean, Russian and Tibetan (so far). 快速语音合成模型，适用于英语、普通话/中文、日语、韩语、俄语和藏语（当前已测试）。

简体中文 | English 并行语音合成 [TOC] 新进展 2021/04/20 合并 wavegan 分支到 main 主分支，删除 wavegan 分支！ 2021/04/13 创建 encoder 分支用于开发语音风格迁移模块！ 2021/04/13 softdtw 分支支持使用 Sof

161 Dec 19, 2022

Command Line Text-To-Speech using Google TTS

cli-tts Thanks to gTTS by @pndurette! This is an interactive command line text-to-speech tool using Google TTS. Just type text and the voice will be p

3 Nov 11, 2022

PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.

VAENAR-TTS - PyTorch Implementation PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.

67 Nov 14, 2022

Chinese real time voice cloning (VC) and Chinese text to speech (TTS).

Chinese real time voice cloning (VC) and Chinese text to speech (TTS). 好用的中文语音克隆兼中文语音合成系统，包含语音编码器、语音合成器、声码器和可视化模块。

6 Nov 8, 2022

Universal End2End Training Platform, including pre-training, classification tasks, machine translation, and etc.

背景安装教程快速上手（一）预训练模型（二）机器翻译（三）文本分类 TenTrans 进阶 1. 多语言机器翻译 2. 跨语言预训练背景 TrenTrans是一个统一的端到端的多语言多任务预训练平台，支持多种预训练方式，以及序列生成和自然语言理解任务。安装教程 git clone git

Tencent Minority-Mandarin Translation Team

42 Dec 20, 2022

A collection of scripts to preprocess ASR datasets and finetune language-specific Wav2Vec2 XLSR models

wav2vec-toolkit A collection of scripts to preprocess ASR datasets and finetune language-specific Wav2Vec2 XLSR models This repository accompanies the

29 Oct 23, 2022

Model for recasing and repunctuating ASR transcripts

Recasing and punctuation model based on Bert Benoit Favre 2021 This system converts a sequence of lowercase tokens without punctuation to a sequence o

88 Dec 29, 2022

A demo of chinese asr

chinese_asr_demo 一个端到端的中文语音识别模型训练、测试框架具备数据预处理、模型训练、解码、计算wer等等功能训练数据训练数据采用thchs_30，

4 Dec 9, 2021

An end to end ASR Transformer model training repo

END TO END ASR TRANSFORMER 本项目基于transformer 6*encoder+6*decoder的基本结构构造的端到端的语音识别系统 Model Instructions 1.数据准备: 自行下载数据，遵循文件结构如下： ├── data │ ├── train │

10 Jul 19, 2022

Comments

Cross-compile issue

Looks like the build system does not respect toolchain/arch setting in menuconfig. Even I set it to arm, it still tries to use x86 toolchain (host system toolchain).

[ 53%] Building C object asr_lib/CMakeFiles/asr_lib.dir/src/asr.c.o cc1: error: bad value (‘armv7-a’) for ‘-march=’ switch cc1: note: valid arguments to ‘-march=’ switch are: nocona core2 nehalem corei7 westmere sandybridge corei7-avx ivybridge core-avx-i haswell core-avx2 broadwell skylake skylake-avx512 cannonlake icelake-client rocketlake icelake-server cascadelake tigerlake cooperlake sapphirerapids alderlake bonnell atom silvermont slm goldmont goldmont-plus tremont knl knm x86-64 x86-64-v2 x86-64-v3 x86-64-v4 eden-x2 nano nano-1000 nano-2000 nano-3000 nano-x2 eden-x4 nano-x4 k8 k8-sse3 opteron opteron-sse3 athlon64 athlon64-sse3 athlon-fx amdfam10 barcelona bdver1 bdver2 bdver3 bdver4 znver1 znver2 znver3 btver1 btver2 native make[2]: *** [asr_lib/CMakeFiles/asr_lib.dir/build.make:76: asr_lib/CMakeFiles/asr_lib.dir/src/asr.c.o] Error 1 make[1]: *** [CMakeFiles/Makefile2:246: asr_lib/CMakeFiles/asr_lib.dir/all] Error 2

opened by mike-2020 0

Releases(v0.1.0)

v0.1.0(Oct 16, 2021)

2021.10.16 upload initial AM&LM files am_xxyy[q].zip: acoustic model, the q means quant to int8 model (about 1/4 size of float model) lmS.zip: Small version language model, 12+6+8MB lmM.zip: Middle version language model, 104+59+72MB lmL.zip: Large version language model, 750+403+72MB
（mega: https://mega.nz/folder/0lwGFLgI#omc_tYjwkl1kLKhZqUG5Ng） font.zip: optional simple GBK font file for embedded display Or you can download from BaiduYunPan: 链接：https://pan.baidu.com/s/1DzTcgi-Q7_T8mnKHfj1R8Q 提取码：wcq8

Files below: ↓↓↓↓↓↓
Source code(tar.gz)
Source code(zip)
am_3316.zip(11.52 MB)
am_3324.zip(20.44 MB)
am_3332.zip(31.48 MB)
am_7332.zip(50.36 MB)
font.zip(1.73 MB)
lmM.zip(146.50 MB)
lmS.zip(15.81 MB)
maix_asr_nezha_D1(2.14 MB)
r329_7332_192.bin(10.98 MB)
r329_toolchain.tar.gz(54.65 MB)

Owner

Sipeed

AIoT opensource hardware platform

GitHub Repository

Wrapper to display a script output or a text file content on the desktop in sway or other wlroots-based compositors

nwg-wrapper This program is a part of the nwg-shell project. This program is a GTK3-based wrapper to display a script output, or a text file content o

94 Dec 27, 2022

ChessCoach is a neural network-based chess engine capable of natural-language commentary.

380 Dec 03, 2022

SimpleChinese2 集成了许多基本的中文NLP功能，使基于 Python 的中文文字处理和信息提取变得简单方便。

SimpleChinese2 SimpleChinese2 集成了许多基本的中文NLP功能，使基于 Python 的中文文字处理和信息提取变得简单方便。声明本项目是为方便个人工作所创建的，仅有部分代码原创。

30 Dec 02, 2022

Research code for the paper "Fine-tuning wav2vec2 for speaker recognition"

Fine-tuning wav2vec2 for speaker recognition This is the code used to run the experiments in https://arxiv.org/abs/2109.15053. Detailed logs of each t

103 Dec 26, 2022

Twitter-Sentiment-Analysis - Twitter sentiment analysis for india's top online retailers(2019 to 2022)

Twitter-Sentiment-Analysis Twitter sentiment analysis for india's top online retailers(2019 to 2022) Project Overview : Sentiment Analysis helps us to

1 Jan 01, 2022

An algorithm that can solve the word puzzle Wordle with an optimal number of guesses on HARD mode.

WordleSolver An algorithm that can solve the word puzzle Wordle with an optimal number of guesses on HARD mode. How to use the program Copy this proje

3 Mar 02, 2022

An end to end ASR Transformer model training repo

10 Jul 19, 2022

Python bot created with Selenium that can guess the daily Wordle word correct 96.8% of the time.

Wordle_Bot Python bot created with Selenium that can guess the daily Wordle word correct 96.8% of the time. It will log onto the wordle website and en

15 Dec 11, 2022

NSFW A chatbot based on GPT2-chitchat

DangBot -- 好怪哦，再来一句卡群怪话bot，powered by GPT2 for Chinese chitchat Training Example: python train.py --lr 5e-2 --epochs 30 --max_len 300 --batch_size 8

11 Jul 21, 2022

Conversational text Analysis using various NLP techniques

159 Jan 06, 2023

Let Xiao Ai speakers control third-party devices

A stupid way to extend miot/xiaoai. Demo for Panasonic Bath Bully FV-RB20VL1 逆向 Panasonic Smart China，获得控制浴霸的请求信息（HTTP 请求），详见 apps/panasonic.py； 2. 通过

14 Jul 07, 2022

Minimal GUI for accessing the Watson Text to Speech service.

Description Minimal graphical application for accessing the Watson Text to Speech service. Requirements Python 3 plus all dependencies listed in requi

1 Oct 22, 2021

Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers

beyond masking Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers The code is coming Figure 1: Pipeline of token-based pre-

23 Sep 27, 2022

This repository consists of a complete guide on natural language processing (NLP) in Python where we'll learn various techniques for implementing NLP including parsing & text processing and understand how to use NLP for text feature engineering.

Python_Natural_Language_Processing This repository contains tutorials on important topics related to Natural Language Processing (NPL). No. Name 01 01

170 Dec 13, 2022

Gold standard corpus annotated with verb-preverb connections for Hungarian.

Hungarian Preverb Corpus A gold standard corpus manually annotated with verb-preverb connections for Hungarian. corpus The corpus consist of the follo

3 Jan 27, 2022

:house_with_garden: Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.

(Framework for Adapting Representation Models) What is it? FARM makes Transfer Learning with BERT & Co simple, fast and enterprise-ready. It's built u

1.6k Dec 27, 2022

Maix Speech AI lib, including ASR, chat, TTS etc.

Related tags

Overview

Maix-Speech

Brief

Build

Clone code by:

Compile

More project structure usage

License

You might also like...

A fast Text-to-Speech (TTS) model. Work well for English, Mandarin/Chinese, Japanese, Korean, Russian and Tibetan (so far). 快速语音合成模型，适用于英语、普通话/中文、日语、韩语、俄语和藏语（当前已测试）。

Command Line Text-To-Speech using Google TTS

PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.

Chinese real time voice cloning (VC) and Chinese text to speech (TTS).

Universal End2End Training Platform, including pre-training, classification tasks, machine translation, and etc.

A collection of scripts to preprocess ASR datasets and finetune language-specific Wav2Vec2 XLSR models

Model for recasing and repunctuating ASR transcripts

A demo of chinese asr

An end to end ASR Transformer model training repo

Comments

Cross-compile issue

Releases(v0.1.0)

v0.1.0(Oct 16, 2021)

Owner

Sipeed

Wrapper to display a script output or a text file content on the desktop in sway or other wlroots-based compositors

ChessCoach is a neural network-based chess engine capable of natural-language commentary.

SimpleChinese2 集成了许多基本的中文NLP功能，使基于 Python 的中文文字处理和信息提取变得简单方便。

Research code for the paper "Fine-tuning wav2vec2 for speaker recognition"

Twitter-Sentiment-Analysis - Twitter sentiment analysis for india's top online retailers(2019 to 2022)

An algorithm that can solve the word puzzle Wordle with an optimal number of guesses on HARD mode.

An end to end ASR Transformer model training repo

Python bot created with Selenium that can guess the daily Wordle word correct 96.8% of the time.

**NSFW** A chatbot based on GPT2-chitchat

Conversational text Analysis using various NLP techniques

Let Xiao Ai speakers control third-party devices

Minimal GUI for accessing the Watson Text to Speech service.

Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers

This repository consists of a complete guide on natural language processing (NLP) in Python where we'll learn various techniques for implementing NLP including parsing & text processing and understand how to use NLP for text feature engineering.

Gold standard corpus annotated with verb-preverb connections for Hungarian.

:house_with_garden: Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.

Data manipulation and transformation for audio signal processing, powered by PyTorch

Calibre recipe to convert latest issue of Analyse & Kritik into an ebook

Comprehensive-E2E-TTS - PyTorch Implementation

A framework for implementing federated learning

NSFW A chatbot based on GPT2-chitchat