whisper VS silero-vad

Let’s not talk about local models as the hardware requirements are way beyond most of these people’s reach. I have a MacBook Air with an M2 chip and 8GB of RAM and can hardly run Whisper locally, so I use this HuggingFace space.

Last week, I launched notesGPT, a free and open source voice note app that has 35,000 visitors, 7,000 users, and over 1,000 GitHub stars so far in the last week. It allows you to record a voice note, transcribes it uses Whisper, and uses Mixtral via Together to extract action items and display them in an action items view. It’s also fully open source and comes equipped with authentication, storage, vector search, action items, and is fully responsive on mobile for ease of use.

I found a pretty good discussion in the topic here:

https://github.com/openai/whisper/discussions/1243

There is a plot of language performance on their repo: https://github.com/openai/whisper

I am not aware of a multi-lingual leaderboard for speech recognition models.

I don't know how OP does it, but here's how I'd do it:

* Generate a transcript by runing Whisper against the podcast audio file: https://github.com/openai/whisper

* Upload transcript to ChatGPT and ask it to summarize.

* Automate all the above.

Ahh, that makes sense. I've been building something like that, but only from other languages into English using Whisper

Whisper already generates subtitles[0], supporting VTT and SRT so this is just a thin wrapper around that.

[0]: https://github.com/openai/whisper/blob/e58f28804528831904c3b...

> although it does require you to wear headphones so the bot doesn't hear itself and get interrupted.

Maybe you can rely on some sort of speaker identification to sort this out?

https://github.com/openai/whisper/discussions/264

v3 only comes in one flavor: large.

I don’t think you’re going to have a good time running the large model on a Pi of any kind.

The large models are 32x slower than the tiny models, roughly.[0]

I’m seeing people report that the Pi 4 can transcribe 30 seconds of audio in somewhere between 30 seconds and 60 seconds with the tiny model.

You can do the math… 32x = 16 minutes to 32 minutes to transcribe 30 seconds of audio with the large model. Not a good time for most people.

The Pi 5 could be 2x to 3x faster.

I should benchmark my Pi 4 sometime (or Pi 5, if it ever shows up).

[0]: https://github.com/openai/whisper/blob/main/README.md#availa...

>How do you detect speech starting and stopping?

https://github.com/snakers4/silero-vad

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

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:

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.

The VAD is always available on Github

I also pinned some interesting comments here regarding mobile and IOT usage here - https://github.com/snakers4/silero-vad/issues/37