Mycroft is the world’s first open source assistant.

Mycroft runs anywhere – on a desktop computer, inside an automobile, or on a Raspberry Pi. This is open source software which can be freely remixed, extended, and improved. Mycroft may be used in anything from a science project to an enterprise software application.

https://mycroft.ai

News
https://mycroft.ai/blog

Mycroft skills
https://mycroftai.github.io/mycroft-skills

Mimic TTS
Mycroft’s Mimic Text to Speech technology. Mimic is now a deep learning based Text-to-Speech (TTS) engine trained on audio recordings from a single speaker.
https://mycroft.ai/blog/mimic-2-is-live

https://github.com/MycroftAI/mimic2


Sources
https://github.com/MycroftAI

Community
https://community.mycroft.ai

Telegram
https://t.me/mycroft_ai


📡 @NoGoolag
#mycroft #assistant #voice #speech #tts

Mozilla publishes the largest public transcribed voice dataset.

Mozilla makes available the largest set of human voices based entirely on crowdsourcing. The data set includes 18 different languages and adds up to nearly 1,400 hours of recorded voice data from more than 42,000 contributors.

From the outset, our vision for Common Voice has been to create the world's most diverse voice dataset, optimized specifically for the development of speech. We have also promised to make the dataset freely accessible so that start-ups, researchers* and anyone else interested in speech technologies can use the high-quality transcribed speech data we have collected.

Today, we are pleased to present our first multilingual dataset, covering 18 languages - including English, French, German and Mandarin (traditional), but also Welsh and Kabyle, for example. This new dataset contains a total of approximately 1,400 hours of voice recordings from more than 42,000 people.

With this release, the Common Voice record is now the largest of its kind, thanks to the support of tens of thousands of people who have brought their voices and written sentences to the Public Domain (CC0). The complete data set is now available for download on the Common Voice page.

Web: https://voice.mozilla.org/en/datasets

📡 @NoGoolag
#mozilla #dataset #voice #crowdsourcing #multilingual #speech

Facebook improving hate speech detection ahead of Myanmar election

(Reuters) - Facebook Inc said on Tuesday that it was preparing for Myanmar’s general election in November by improving the detection and removal of hate speech and content that incites violence and preventing the spread of misinformation.

The company said in a blog that between now and Nov. 22, it would remove “verifiable misinformation and unverifiable rumours” that are assessed as having the potential to suppress the vote or damage the “integrity” of the electoral process.

“For example, we would remove posts falsely claiming a candidate is a Bengali, not a Myanmar citizen, and thus ineligible,” Facebook said.

https://www.reuters.com/article/us-myanmar-election-facebook/facebook-improving-hate-speech-detection-ahead-of-myanmar-election-idUSKBN25S3H9

#Asia #Myanmar #hate #speech #Facebook

Facebook India grilled over hate speech, alleged bias

NEW DELHI (AP) — Facebook India executives were grilled Wednesday by members of a parliamentary committee on information technology over the company’s alleged political bias and role in spreading hate speech in India.

The closed-door hearing followed accusations in newspaper reports that Facebook was allowing anti-Muslim hate speech on the platform and that its top policy official in India had shown favoritism toward Prime Minister Narendra Modi’s Bharatiya Janata Party. The social media giant has denied the allegations.

The outcome of the hearing was unclear.

India is Facebook’s largest market with nearly 328 million users. Facebook also owns WhatsApp, which has more than 400 million users in India.

https://apnews.com/d39c2b46ce80211bfd6431c3c13f51a5

#Asia #India #Facebook #executives #hate #speech

Linux Foundation Introduces Open Voice Network

https://www.linuxfoundation.org/press-release/linux-foundation-introduces-open-voice-network-to-prioritize-trust-and-interoperability-in-a-voice-based-digital-future/

https://openvoicenetwork.org

Comments
https://news.ycombinator.com/item?id=27673681

#voice #speech

Vosk Speech Recognition Toolkit

Vosk is an offline open source #speech #recognition toolkit. It enables speech recognition for 20+ languages and dialects - English, Indian English, German, French, Spanish, Portuguese, Chinese, Russian, Turkish, Vietnamese, Italian, Dutch, Catalan, Arabic, Greek, Farsi, Filipino, Ukrainian, Kazakh, Swedish, Japanese, Esperanto, Hindi, Czech. More to come.

Vosk models are small (50 Mb) but provide continuous large vocabulary transcription, zero-latency response with streaming API, reconfigurable vocabulary and speaker identification.

Speech recognition bindings implemented for various programming languages like Python, Java, Node.JS, C#, C++ and others.

Vosk supplies speech recognition for chatbots, smart home appliances, virtual assistants. It can also create subtitles for movies, transcription for lectures and interviews.

Vosk scales from small devices like Raspberry Pi or Android smartphone to big clusters.

https://t.me/speech_recognition

https://alphacephei.com/vosk

https://github.com/alphacep/vosk-api

Wenet

Automatic #Speech #Recognition toolkit.

https://github.com/wenet-e2e/wenet

https://wenet.org.cn/wenet/

#Australian #eSafety commissioner Julie Inman #Grant tells the World Economic Forum we need a "recalibration" of #freedom of #speech.

"We are finding ourselves in a place where we have increasing polarization everywhere, and everything feels binary when it doesn't need to be - so I think we're going to have to think about a recalibration of a whole range of human rights that are playing out online - from freedom of speech, to be free from online violence.

Or the right of data protection, to the right of child dignity," .....

whatever that last part means...... 🤷‍♂

https://writeout.ai

#Transcribe and #translate any #audio file. 100% free to use.

This website with source code available (it can be hosted locally) allows you to upload any audio file and receive a transcription and/or text translation. It uses OpenAI's Whisper API on the back end.

Source on GitHub:
https://github.com/beyondcode/writeout.ai

#writeout #ai #speech #recognition

#Speech Note Transcribes #Voice to #Text on #Linux

https://www.omglinux.com/speech-note-transcribe-voice-to-text-on-linux/

FUTO Voice Input

Android application that lets you do speech-to-text on Android, integrating with third party keyboards or apps that use the generic speech-to-text APIs.

👉 FUTO Voice website: https://voiceinput.futo.org
👉 F-Droid repo:
https://app.futo.org/fdroid/repo/
👉 FUTO Voice play store: https://play.google.com/store/apps/details?id=org.futo.voiceinput
👉 FUTO Voice source code: https://gitlab.futo.org/alex/voiceinput
⚠️ License https://gitlab.futo.org/alex/voiceinput/-/blob/master/FTL_LICENSE.md

🔵 Linux Live Captions interview: https://www.youtube.com/watch?v=r09Hm2zd2lY
👉 Live Captions github: https://github.com/abb128/LiveCaptions
🔵 Louis' interview w/ FUTO's founder:  
Q&A w/ billionaire alt-tech investor/philanthropist Eron Wolf
https://www.youtube.com/watch?v=OJPmbcU-Vzo
⚠️ Google's breaches of privacy have gone TOO FAR!
https://www.youtube.com/watch?v=_vWAF13KigI

00:00 - Intro
00:24 - The problem with voice to text
00:37 - How Google's voice to text stored data
01:24 - EULA roofying
02:21 - Why is this called paid promotion?
03:37 - Introducing our voice to text keyboard
04:00 - The issue with Google's voice to text
04:30 - Demoing Google's voice to text
04:58 - Installing FUTO Voice Input
05:26 - Configuring FUTO Voice Input
05:52 - A note on compatible keyboards
06:19 - Configuring FUTO Voice Input
06:42 - Demoing FUTO Voice Input - SLOW MODEL
07:54 - Demoing FUTO Voice Input - FAST MODEL
08:28 - Demoing Google Voice input - same text
08:52 - FUTO keyboard wins out - better accuracy & punctuation
09:34 - NO DATA COLLECTION, NO ADS, NO TRACKING
09:58 - Open Source, but not free
10:18 - Our DRM/antipiracy measure is the honor system
10:48 - Why isn't this free?
12:00 - We will be making a keyboard w/ autocorrect soon as well

#Android #speech #recognition #stt #voice

#Linux Desktop application that provides live #captioning

FUTO Fellowship program interview; linux captions software

👉 Live Captions github: https://github.com/abb128/LiveCaptions

🔵 Q&A w/ billionaire alt-tech investor/philanthropist Eron Wolf
https://www.youtube.com/watch?v=OJPmbcU-Vzo
🔵 FUTO Fellows program: https://futo.org/fellows/
🔵 FUTO Youtube channel - @futotech
⚠️ Google's breaches of privacy have gone TOO FAR!
https://www.youtube.com/watch?v=_vWAF13KigI

#speech #recognition #stt #voice