A Python wrapper for simple offline real-time dictation (speech-to-text) and speaker-recognition using Vosk.

Overview

Simple-Vosk

A Python wrapper for simple offline real-time dictation (speech-to-text) and speaker-recognition using Vosk. Check out the official Vosk GitHub page for the original API (documentation + support for other languages).

This module was created to make using a simple implementation of Vosk very quick and easy. It is intended for rapid prototyping and experimenting; not for production use.

For example, I used this module in a quick personal-assistant program.

Features

  • Uses Vosk: lightweight, multilingual, offline, and fast speech recognition.
  • Runs in background thread (non-blocking).
  • Both complete-sentence and real-time outputs.
  • Optional speaker-recognition (using X-Vectors).
  • Configurable filter-phrase list (eliminate common false outputs).

Requirements

Should work with Python 3.6+. Tested with Python 3.8.7 on Windows 10 1903.

Python Modules: (see requirements.txt)

  • vosk
  • sounddevice
  • numpy

You will also need to download Vosk models; one for your language of choice, and (if desired) the speaker-recognition model. Both can be found on the Vosk models page. If you don't use speaker recognition, you only need the one model.

Examples

This repository contains some examples of usage; ExampleSimpleDictation.py, ExampleSpeakerRecognition.py, and ExampleNonBlocking.py. Check the Documentation.md file for more in-depth info.

Below is the simplest implementation to get a fully-functioning speech-recognition system.

import simpleVosk as sv

def prnt(txt, spk, full):
	print(txt)

s = sv.Speech(callback=prnt, model="model")
s.run(blocking=True)

Troubleshooting

Make sure your default input device is working, and/or ensure you are passing the correct DeviceID to the Speech object. You can see device IDs with the listDevices() method in simpleVosk.py.

Make sure you have Windows microphone access enabled. Having this disabled can cause errors similar to this: sounddevice.PortAudioError: Error opening RawInputStream: Unanticipated host error [PaErrorCode -9999]: 'Undefined external error.' [MME error 1]

A Note on Conventions

This project goes against some standard Python conventions:

  • It uses camelCase for naming methods (and files) rather than snake_case
  • Tabs are used rather than 4 spaces for indentation (as I am a sane human being)
  • Non-standard docstring formats are being used

Future Plans

  • Add ability to add custom words/phrases (KaldiRecognizer appears to only accept replacement dictionaries)
  • Use proper docstrings
Gathers machine learning and Tensorflow deep learning models for NLP problems, 1.13 < Tensorflow < 2.0

NLP-Models-Tensorflow, Gathers machine learning and tensorflow deep learning models for NLP problems, code simplify inside Jupyter Notebooks 100%. Tab

HUSEIN ZOLKEPLI 1.7k Dec 30, 2022
Code for "Generative adversarial networks for reconstructing natural images from brain activity".

Reconstruct handwritten characters from brains using GANs Example code for the paper "Generative adversarial networks for reconstructing natural image

K. Seeliger 2 May 17, 2022
ADCS - Automatic Defect Classification System (ADCS) for SSMC

Table of Contents Table of Contents ADCS Overview Summary Operator's Guide Demo System Design System Logic Training Mode Production System Flow Folder

Tam Zher Min 2 Jun 24, 2022
Mycroft Core, the Mycroft Artificial Intelligence platform.

Mycroft Mycroft is a hackable open source voice assistant. Table of Contents Getting Started Running Mycroft Using Mycroft Home Device and Account Man

Mycroft 6.1k Jan 09, 2023
Japanese NLP Library

Japanese NLP Library Back to Home Contents 1 Requirements 1.1 Links 1.2 Install 1.3 History 2 Libraries and Modules 2.1 Tokenize jTokenize.py 2.2 Cabo

Pulkit Kathuria 144 Dec 27, 2022
Repository for the paper "Optimal Subarchitecture Extraction for BERT"

Bort Companion code for the paper "Optimal Subarchitecture Extraction for BERT." Bort is an optimal subset of architectural parameters for the BERT ar

Alexa 461 Nov 21, 2022
Code associated with the Don't Stop Pretraining ACL 2020 paper

dont-stop-pretraining Code associated with the Don't Stop Pretraining ACL 2020 paper Citation @inproceedings{dontstoppretraining2020, author = {Suchi

AI2 449 Jan 04, 2023
This repository structures data in title, summary, tags, sentiment given a fragment of a conversation

Understand-conversation-AI This repository structures data in title, summary, tags, sentiment given a fragment of a conversation How to install: pip i

Juan Camilo López Montes 1 Jan 11, 2022
Klexikon: A German Dataset for Joint Summarization and Simplification

Klexikon: A German Dataset for Joint Summarization and Simplification Dennis Aumiller and Michael Gertz Heidelberg University Under submission at LREC

Dennis Aumiller 8 Jan 03, 2023
ASCEND Chinese-English code-switching dataset

ASCEND (A Spontaneous Chinese-English Dataset) introduces a high-quality resource of spontaneous multi-turn conversational dialogue Chinese-English code-switching corpus collected in Hong Kong.

CAiRE 11 Dec 09, 2022
Implementation of TF-IDF algorithm to find documents similarity with cosine similarity

NLP learning Trying to learn NLP to use in my projects! Table of Contents About The Project Built With Getting Started Requirements Run Usage License

Faraz Farangizadeh 3 Aug 25, 2022
Ceaser-Cipher - The Caesar Cipher technique is one of the earliest and simplest method of encryption technique

Ceaser-Cipher The Caesar Cipher technique is one of the earliest and simplest me

Lateefah Ajadi 2 May 12, 2022
ChainKnowledgeGraph, 产业链知识图谱包括A股上市公司、行业和产品共3类实体

ChainKnowledgeGraph, 产业链知识图谱包括A股上市公司、行业和产品共3类实体,包括上市公司所属行业关系、行业上级关系、产品上游原材料关系、产品下游产品关系、公司主营产品、产品小类共6大类。 上市公司4,654家,行业511个,产品95,559条、上游材料56,824条,上级行业480条,下游产品390条,产品小类52,937条,所属行业3,946条。

liuhuanyong 415 Jan 06, 2023
Pipeline for chemical image-to-text competition

BMS-Molecular-Translation Introduction This is a pipeline for Bristol-Myers Squibb – Molecular Translation by Vadim Timakin and Maksim Zhdanov. We got

Maksim Zhdanov 7 Sep 20, 2022
Code for lyric-section-to-comment generation based on huggingface transformers.

CommentGeneration Code for lyric-section-to-comment generation based on huggingface transformers. Migrate Guyu model and code (both 12-layers and 24-l

Yawei Sun 8 Sep 04, 2021
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 09, 2021
In this repository we have tested 3 VQA models on the ImageCLEF-2019 dataset.

Med-VQA In this repository we have tested 3 VQA models on the ImageCLEF-2019 dataset. Two of these are made on top of Facebook AI Reasearch's Multi-Mo

Kshitij Ambilduke 8 Apr 14, 2022
Reading Wikipedia to Answer Open-Domain Questions

DrQA This is a PyTorch implementation of the DrQA system described in the ACL 2017 paper Reading Wikipedia to Answer Open-Domain Questions. Quick Link

Facebook Research 4.3k Jan 01, 2023
A Multi-modal Model Chinese Spell Checker Released on ACL2021.

ReaLiSe ReaLiSe is a multi-modal Chinese spell checking model. This the office code for the paper Read, Listen, and See: Leveraging Multimodal Informa

DaDa 106 Dec 29, 2022