Some good transcription solutions: https://zapier.com/blog/best-text-dictation-software/#windowsspeech https://otter.ai/ (Haven't actually tried Otter, but it gets a LOT of good reviews.). - Source: Hacker News / 5 days ago

Of course, there are many existing solutions like Otter.ai or Fathom in the market. But in case you want to build a tool yourself and customize the output of it, then you are on the same page as me. To develop this application, we will use Unbody to convert input video transcriptions into intelligence/generative content and Appsmith to make it easy to design and build the UI of our app without extensive front-end... - Source: dev.to / 6 months ago

This is weird but I wonder if you could use something like https://otter.ai/. Record your notes as you are going. That should give you at least text of all of your welds. You’d still have to punch it later. Seems like there’s got to be a better way to do this. Stopping every time to break your flow sounds like a huge pain in the ass. Curious what you come up with. Source: 6 months ago

Is there any app from otter.ai that you run on personal machine? How does otter.ai process 4 different audio streams? Source: 6 months ago

Job laptop -> 3.5mm aux (this turns into speaker output) -> 3.5mm mic/audio splitter (this turns into microphone input) -> 3.5mm to usb-c adapter (cause my macbook only has 1 3.5mm aux) --> now the personal macbook has a new "mic input" from the job laptop. Which you can use to pipe audio into otter.ai to transcribe audio. You have to manually name them, but they learn in subsequent meetings. Source: 6 months 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: about 1 year 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