I can't help but feel jealous and bitter when I come across a news article or whisper.sh message about how people found their true love. Some stories for example about a lady who was nearly murdered by her abusive ex and eventually married the paramedic that saved her life. Also a story about a man about to commit suicide only to receive a mysterious phone call from someone who would eventually become his wife. Source: about 2 years ago

Tbh, I'm surprised it took this long for the app to be taken down. It was 99% scammers. You can verify the app has been taken down by visiting their website and clicking get app. The play store doesn't take you to link to download it and if you search for "whisper," it doesn't show up at all. It use to be the first search result. Source: about 2 years ago

It's probably because these things were gotten from the Whisper app. Source: over 2 years ago

You do get a lot of scraper sites, but then you also get some weird ones. Someone used one of my drawings as a backdrop to a confession on whisper.sh. Pixsy found it. They also found a site that was offering free HD wallpaper downloads (no idea where they would have gotten an HD image file since I don't post those just anywhere) and they had one of my paintings on their site. Source: over 2 years ago

I don't know about a Whisper dating app but there's a whisper.sh website where people are anonymous and do confessions and venting and such. Careful, some of the stuff there is dirty. Source: almost 3 years ago

>How do you detect speech starting and stopping? https://github.com/snakers4/silero-vad. - Source: Hacker News / 7 months ago

You could look into https://github.com/guillaumekln/faster-whisper especially the VAD section (Voice Activity Detector) using https://github.com/snakers4/silero-vad. Source: 11 months ago

I also had the same synchronization issue, so I wrote a WebUI/CLI that uses Silero-VAD that first splits the audio whenever there a silent portion (or every 30 seconds), and I haven't experienced it since:. Source: 12 months ago

By the way, I've updated the WebUI to now also support using Silero VAD to break up the audio into distinct sections, and run Whisper on each section and then combine them into one single transcript/SRT file. Source: over 1 year ago

And while googling this, I stumbled upon this discussion on the Whisper GitHub repository, which seems to suggest that the issue is that the current VAD (Voice Activity Detection) is quite poor, and that it can be resolved by using another VAD (like silero-vad). This might be something I want to add to my WebUI in the future. Source: over 1 year ago