https://github.com/OpenVoiceOS/ovos-stt-plugin-vosk

vosk STT plugin for mycroft
https://github.com/OpenVoiceOS/ovos-stt-plugin-vosk

asr automatic-speech-recognition hacktoberfest kaldi speech-recognition speech-to-text stt vosk

Last synced: about 2 months ago
JSON representation

vosk STT plugin for mycroft

• Host: GitHub
• URL: https://github.com/OpenVoiceOS/ovos-stt-plugin-vosk
• Owner: OpenVoiceOS
• License: apache-2.0
• Created: 2020-12-03T04:21:47.000Z (over 3 years ago)
• Default Branch: dev
• Last Pushed: 2024-01-13T22:55:20.000Z (6 months ago)
• Last Synced: 2024-05-18T14:14:13.528Z (about 2 months ago)
• Topics: asr, automatic-speech-recognition, hacktoberfest, kaldi, speech-recognition, speech-to-text, stt, vosk
• Language: Python
• Homepage:
• Size: 60.5 KB
• Stars: 14
• Watchers: 4
• Forks: 6
• Open Issues: 2
• Metadata Files:
  • Readme: readme.md
  • Changelog: CHANGELOG.md

Lists

• awesome-ovos-plugins - ovos-stt-plugin-vosk

README

        
## Description

Mycroft STT plugin for [Vosk](https://alphacephei.com/vosk/)

## Install

`pip install ovos-stt-plugin-vosk`

You can download official models from [alphacephei](https://alphacephei.com/vosk/models)

## Configuration

You need to download a kaldi model or provide a direct download url

```json

  "stt": {

    "module": "ovos-stt-plugin-vosk",

    "ovos-stt-plugin-vosk": {

        "model": "/path/to/unzipped/model/folder"

    }

  }

 

```

### Advanced configuration

```json

  "stt": {

    "module": "ovos-stt-plugin-vosk-streaming",

    "ovos-stt-plugin-vosk-streaming": {

        "model": "http://alphacephei.com/vosk/models/vosk-model-small-en-us-0.15.zip",

        "verbose": true

    },

    "ovos-stt-plugin-vosk": {

        "model": "http://alphacephei.com/vosk/models/vosk-model-small-en-us-0.15.zip"

    }

  }

 

```

`ovos-stt-plugin-vosk` - regular STT, transcription happens after recording finishes

`ovos-stt-plugin-vosk-streaming` - streaming STT, transcription happens real time

`verbose` - print partial transcriptions

`model` - full path or direct download url for model

`lang` - optional, if `model` not provided will download default small model (if it exists)

## Docker

This plugin can be used together with [ovos-stt-http-server](https://github.com/OpenVoiceOS/ovos-stt-http-server) 

```bash

docker run -p 8080:8080 ghcr.io/openvoiceos/vosk-stt-http-server:master

```