Viewing profile — BetterWhisper
BetterWhisper
HN member- Joined
- Mon, Nov 13, 2023, 9:28 AM UTC
- HN karma
- 16
- Public activity
- 25 items
- HN profile
- View on Hacker News ↗
About BetterWhisper
Recent public activity
-
comment
Comment #47433019
What scraping challenges? From your pricing I can say you are just using other APIs and you are a layer on top of them. Also your docs mix insta and TikTok results
-
comment
Comment #44890441
Hey, indeed Whisper can do the transcription of Japanese and even the translation (but only to English). For the best results you need to use the largest model which depending on y…
- story
-
comment
Comment #44576283
Do you support speaker recognition?
-
comment
Comment #42940725
Not a 8 min read as stated in the beginning but nevertheless interesting.
-
comment
Comment #42655304
In "The proof as we know" section he states that the dot is a NAND operation Quote: "the · dot here can be thought of as representing the Nand operation"
-
comment
Comment #41770437
Are you running whisper on that same $7 Server?
-
comment
Comment #41690244
https://www.videototextai.com/ - an AI transcription, translation, chat with your video/audio platform. We are very close to releasing an update where it is possible to caption any…
-
comment
Comment #41342545
We're currently developing https://www.videototextai.com/ – ChatGPT for video and audio. The idea is to get to an all-in-one video and audio editing/insights platform. We’re active…
-
comment
Comment #41203323
You are allowed to delete any transcription you make and with that we do not keep any copy of the transcripts :) . The cookie banner is there to comply with the EU laws.
-
comment
Comment #41200408
If you are looking for something automatic that also allows you to interact with your transcripts chatgpt style then I would recommend https://www.videototextai.com/
-
comment
Comment #41197042
https://github.com/Emerge-Lab/gpudrive - the repo
-
comment
Comment #41147219
Conclusion references a tweet by Elon to explain the most obvious solution is the most entertaining... Make of it what you want
-
comment
Comment #41146754
Does it do speaker recognition/ diarization? Can't see it from the repo readme
-
comment
Comment #40541353
Well, do you have the hardware to self-host? People nowadays usually are not okay with 1 week of downloading a torrent like it was in 2005. That is probably how long the embedding …
-
comment
Comment #40533392
Reading the notes aloud is a really good solution without having to spend a ton of time on trying to OCR handwriting. I can recommend https://www.videototextai.com/ for transcribin…
-
comment
Comment #40025801
Developed https://www.videototextai.com/ exactly for this reason as it was quite impossible to search videos otherwise. Also you can copy the transcript into a LLM and ask question…
-
comment
Comment #39858618
[flagged]
-
comment
Comment #38970567
All of it, I have tested it and want to automate it currently. Edit: the biggest hurdle previously was no midjourney API. Now that DALLE-3 is released it is good enough and has an …
-
comment
Comment #38922612
And what is this unique opportunity to lead in AI?
-
comment
Comment #38734850
Still no API...
-
comment
Comment #38284266
Literally spent the last hour trying to figure out why my app was failing. Only thing I was seeing from my side is "permission denied". why can't Google be bothered to put outages …
-
comment
Comment #38283991
Literally spent the last hour trying to figure out why my app was failing when Google can not even be bothered to put outages in Firebase console... Pretty sure this affected Hacke…
-
comment
Comment #38248530
While it seems YouTube's auto-generated are hit or miss, I wonder if feeding them through an LLM can fix the mistakes and still get the video's idea out of them
-
comment
Comment #38248502
Wow, why are they so expensive? Like even the regular whisperAPI by OpenAI is less expensive. This is also why I decided to create https://www.betterwhisperapi.com/ . I believe mos…