Evolution of Home Assistant:
- Runs on Raspberry Pi, controls a single WiFi light switch
- Controls a dozen switches and plugs
- Automations using Phone locations and time of day
- AddOns! Mosquitto, AdGuard Home and MotionEye/Frigate get installed
- Migrates to beefier server
- Voice and Whisper addons get installed
- Zigbee takes over for switches and plugs
- What's next?
Last night, I gave Whisper a scritch and the fluff dent gave her a bit of a reverse mohawk.
Or perhaps a hint of Gossamer, the hairy monster that chases Bugs Bunny.
Random Old Comic: Improvised Weaponry https://www.toyboxcomix.com/2018/12/28/improvised-weaponry/ Improvised Weaponry #Jetstorm #Megatron #OptimusPrime #Runway #Sonar #Stormcloud #Transformers #Visper #Whisper
I've spent a lot of time recently talking to my computer. Not conversing with it but talking at it... Put another way I'm a born again speech-to-text fanatic. It lowers the barriers to blogging and journalling for me. I wrote about my recent experiences #blogging #stt #journalling #whisper https://brainsteam.co.uk/2025/4/14/voice-input-is-awesome/
Is there any open source app (e.g. via #FDroid for speech transcription on Android? I would like to share audio with this app which then does the transcription offline on my device.
Anything with #Whisper or #CommonVoice models would be great.
HowTo Explains how to install and activate the OpenVINO plug-in in Audacity. This LLM is installed locally on your computer meaning that nothing gets transmitted to a remote servers. After installation, Audacity gains music separation, AI noise suppression, music generation and audio transcription. #Audacity #OpenVino #TTMO #HowTo #Intel #AI #Whisper, #Transcription, #SpeechToText, #MusicGeneration, #NoiseSuppression
https://www.alanbonnici.com/2025/04/howto-install-openvino-ai-plug-in-in.html
Как я делал голосового ассистента на NLP и не сошел с ума
Голосовые ассистенты давно перестали быть просто игрушкой — теперь это полноценные цифровые помощники, которые умеют общаться, искать информацию и даже шутить (иногда лучше некоторых людей). В этой статье разберём, как собрать своего кастомного ассистента с нуля на Python, используя современные NLP-инструменты. Без Siri, без Alexa, всё своё, родное.
Slowly and carefully, Whisper inches closer to the Beef Stroganoff.
Added a thing to generate code through Ollama if you set a flag on the command line.
It's... well, a work in progress.
Слушать некогда читать: где поставим запятую?
Узнаете, когда заглянете под кат. Для затравочки: речь пойдёт про инструмент ЮMoney для транскрибации аудио с внутренних созвонов в тексты и про кое-что ещё для наших клиентов.
I get this “easter egg” when using whisper.cpp to transcribe audio:
```
Subtítulos realizados por la comunidad de Amara.org
0:27:19 - 0:27:22
```
That’s not part of the text, but Whisper inserts it at the end of voice transcripts. It’s baked into the AI model because OpenAI trained on movies with community-generated subtitles.
Apparently, it happens often – there's a github ticket filled with anecdotes (pictured): https://github.com/openai/whisper/discussions/928
Whisper has decided she’d rather not know what the man is doing on the cover of that book.
Today in BoneQuest History for March 19th 2006 "PERFORMANCE ART" https://bonequest.com/2698 #bonequest #cocksucking #deuce_solo #drunk_deuce #grunt #performance_art #pig #whisper
Apple Silicon Mac上で自動話者認識をサポートしたAI文字起こしアプリ「MacWhisper/Whisper Transcription Pro v12.0」がリリース。
https://applech2.com/archives/20250316-macwhisper-support-automatic-speaker-recognition.html