frogbase VS generate-subtitles

If you’re looking to use a local deployment and are comfortable with python projects, this deployment was fairly easy to use: https://github.com/hayabhay/whisper-ui

I recommend using chat GPT to learn some very basic python/programming tho. I like this one https://github.com/hayabhay/whisper-ui which uses streamlit for easy to use UI for bulk transcriptions.

This tool 2 out of the 4 items you mentioned: https://github.com/hayabhay/whisper-ui

What utilities related to Whisper do you wish existed? What have you had to build yourself?

On the end user application side, I wish there was something that let me pick a podcast of my choosing, get it fully transcribed, and get an embeddings search plus answer q&a on top of that podcast or set of chosen podcasts. I've seen ones for specific podcasts, but I'd like one where I can choose the podcast. (Probably won't build it)

Also on the end user side, I wish there was an Otter alternative (still paid $30/mo, but unlimited minutes per month) that had longer transcription limits. (Started building this, not much interest from users though)

Things I've seen on the dev tool side:

Gladia (API call version of Whisper)

Whisper.cpp

Whisper webservice (https://github.com/ahmetoner/whisper-asr-webservice) - via this thread

Live microphone demo (not real time, it still does it in chunks) https://github.com/mallorbc/whisper_mic

Streamlit UI https://github.com/hayabhay/whisper-ui

Whisper playground https://github.com/saharmor/whisper-playground

Real time whisper https://github.com/shirayu/whispering

Whisper as a service https://github.com/schibsted/WAAS

Improved timestamps and speaker identification https://github.com/m-bain/whisperX

MacWhisper https://goodsnooze.gumroad.com/l/macwhisper

Crossplatform desktop Whisper that supports semi-realtime https://github.com/chidiwilliams/buzz

Github Repo: https://github.com/hayabhay/whisper-ui

People may also like this tool which is a bit more about searching the contents. https://github.com/hayabhay/whisper-ui

There is whisper ui to create meta data (speech 2 text).

They generate .SRT files, and you can view their repository there.

I use this script to generate text layers based on the srt file I got by using this website.

I do a lot of transcriptions in my job, most of the websites suggested in other comments requiere an account and payments, https://freesubtitles.ai is free and you don’t need an account, you could pay to get premium services but it’s not mandatory

The translation part most likely won't work out all that well, but for JAV (˵ ͡° ͜ʖ ͡°˵) I've used https://freesubtitles.ai/ to get the original audio in subtitle format and then used DeepL to get it translated to English. DeepL doesn't support Hebrew though, but I also tried the AWS' whateveritwascalled and it was okay-ish, maybe check out if they support it.

You can download the audio and then get a transcript/subtitles with freesubtitles.ai

Hey guys I am the developer of https://freesubtitles.ai, I am really satisfied with the quality of the transcriptions now and wanted to share it around a bit, you can use it to transcribe content from over 100 different languages and automatically translate it to over 100 different languages for free. I have been using it to watch movies in foreign languages and it works pretty well, hope it can serve as an alternative to trying to find already made subtitles online, cheers!

I just finished my free transcription app and wanted to share it around a bit. You can use it to transcribe content in over 100 languages and have it translated to over 100 languages all for free. Hope this can be useful in some way, cheers! https://freesubtitles.ai

Whisper AI is a game changer as far as transcribing lyrics don’t know if genius is up on it /u/grinchnight14. https://freesubtitles.ai/ for free without needing to do any coding