Free & Accurate Transcription Tool Powered By OpenAI
I've been working on something called ListenMonster, and I think it might be helpful for some of you. I've tried a bunch of transcription tools, and honestly, most of them left me frustrated. They were using AWS or Azure APIs, and the accuracy wasn't there.
So, I decided to create ListenMonster, using something called Whisper. It's more accurate, and the best part? It's free. No need to sign up or wait in a queue. Just upload your media files, and it'll transcribe them instantly.
I'm not trying to sell anything here; I have some GPU available, so I build this website. I just thought it might be useful for some of you who are struggling with the same issues I had. Check it out at https://listenmonster.com if you're interested, and let me know what you think.
Thanks!
Forum rules
Under no circumstances is spamming or advertising of any kind allowed. Do not post any abusive, obscene, vulgar, slanderous, hateful, threatening, sexually-orientated or any other material that may violate others security. Profanity or any kind of insolent behavior to other members (regardless of rank) will not be tolerated. Remember, what you don’t find offensive can be offensive to other members. Please treat each other with the kind of reverence you’d expect from other members.
Failure to comply with any of the above will result in users being banned without notice. If any further details are needed, contact: “The team” using the link at the bottom of the forum page. Thank you.
Under no circumstances is spamming or advertising of any kind allowed. Do not post any abusive, obscene, vulgar, slanderous, hateful, threatening, sexually-orientated or any other material that may violate others security. Profanity or any kind of insolent behavior to other members (regardless of rank) will not be tolerated. Remember, what you don’t find offensive can be offensive to other members. Please treat each other with the kind of reverence you’d expect from other members.
Failure to comply with any of the above will result in users being banned without notice. If any further details are needed, contact: “The team” using the link at the bottom of the forum page. Thank you.
-
listenMonster
- Posts: 4
- Joined: Thu Aug 31, 2023 10:34 am
Re: Free & Unlimited Transcription Tool
I gave it a try. Speech recognition is first rate, but timing is terrible.
Subtitle Edit also has a Whisper based audio to SRT feature and timing is also an issue.
This seems to be a failing of OpenAI itself. Hopefully they will improve it.
ListenMonster also has a 100 MB size limit, so mono 80 kb aac is your best option for long videos.
In spite of the timing issues, a free and accurate speech to text service is more then welcome!
Subtitle Edit also has a Whisper based audio to SRT feature and timing is also an issue.
This seems to be a failing of OpenAI itself. Hopefully they will improve it.
ListenMonster also has a 100 MB size limit, so mono 80 kb aac is your best option for long videos.
In spite of the timing issues, a free and accurate speech to text service is more then welcome!
-
listenMonster
- Posts: 4
- Joined: Thu Aug 31, 2023 10:34 am
Re: Free & Unlimited Transcription Tool
yes it was problem, however we fixed it today. Kindly check now, thank you for visiting website
Re: Free & Unlimited Transcription Tool
It is much better, but still has the problem I mentioned before about Whisper.
Timing will be fine for a few sentence's and then subs will lead audio by 10-15 seconds for awhile and then go back in sync.
You really have to go through it line by line to properly correct the sync.
And since subs lead the audio, it's best to work from the end to the beginning, because you're always sliding subs to the right.
It's still a big help. The speech recognition is amazing.
I hope you'll continue to make progress with the timing issue, but I think it may be a root problem with OpenAI/Whisper.
Do you know of any paid service that has used Whisper to create acceptable subtitles?
Timing will be fine for a few sentence's and then subs will lead audio by 10-15 seconds for awhile and then go back in sync.
You really have to go through it line by line to properly correct the sync.
And since subs lead the audio, it's best to work from the end to the beginning, because you're always sliding subs to the right.
It's still a big help. The speech recognition is amazing.
I hope you'll continue to make progress with the timing issue, but I think it may be a root problem with OpenAI/Whisper.
Do you know of any paid service that has used Whisper to create acceptable subtitles?
-
listenMonster
- Posts: 4
- Joined: Thu Aug 31, 2023 10:34 am
Re: Free & Unlimited Transcription Tool
Please forward some files on [email protected] I will check them personally, let me see if I can do something about it
-
ai.opensubtitles.com
- Posts: 18
- Joined: Fri Dec 29, 2023 4:21 pm
- Location: Planet Earth
- Contact: Website
Re: Free & Unlimited Transcription Tool
Are you using the large model of Whisper?
I agree that it improved a bit compared with a year ago. But AWS is still better. Did you try AssemblyAI?
I'm always testing AI models to add them to https://ai.opensubtitles.com .
I agree that it improved a bit compared with a year ago. But AWS is still better. Did you try AssemblyAI?
I'm always testing AI models to add them to https://ai.opensubtitles.com .
Who is online
Users browsing this forum: No registered users and 22 guests