Remixing songs using Chat GPT-4 and the command line

matej — Thu, 16 Mar 2023 15:16:24 +0000

I've recently heard a song that I really liked, and I've thought about how I wanted the tempo to be a bit slower.

We've all heard Youtube "slowed, reverbed, bass boosted" versions of popular radio songs.

Just playing it at 0.9x at Youtube wasn't going to be enough!

Since we just got GPT-4 available and it's all the rage, I've decided to go to it and prompt it for the tips.

First prompt was pretty basic -



Could I do a basic song (mp3) remix via ffmpeg

and the answer was more in the line of mixing different songs together, so I had to be a bit more direct.



It's more in the line that I have extracted vocals from a song, and a separate track for the instrumental of the song and I want to slow the instrumental by some 12 %, add bass boost and slight reverb, and then merge that again with the vocals, is that possible with ffmpeg?

I got back the following -

But then my session crashed and I realized I forgot to copy actual commands :).

After a bit of back and forth with OpenAI's GPT and "Sidney" via Edge chat - I got the following pipeline to make a decent result -

Slow it down



ffmpeg -i input.mp3 -filter: a "atempo=0.89" slowed_input.mp3

Add some boost to bass frequencies



ffmpeg -i slowed_input.mp3 -af "equalizer=f=100:width_type=h:200:g=6" input_boosted.mp3

Add reverb with sox



sox input_boosted.mp3 reverb_input.mp3 reverb 30 50 100 50 0

And this is the result

I've also prompted GPT for a statement that I own no copyright of the song for Youtube video description (legal purposes), in Croatian (!!) and it handled that pretty well.

NOTES

I had to use sox, because there is some mismatch between my Fedora version of ffmpeg and it's filters to add reverb
As you'll notice I've ignored my first idead to split the track into vocals and instrumental, since that ended me up with a too big of a mismatch between vocals and the music track
When applying bass boost, the effect is modulated with the last 'g' variable, sometimes more than 5 gives loud thumps one would have to further clean
There is ample room to play with the reverb effect but I like this as it's quick and dirty
At times Sidney straight up refuses to give you a direct ffmpeg or sox command

This is another one in my line of experimenting building stuff with the tiny shoggoths that LLMs are.

I've been using it as a math tutor, CRUD coding buddy, and to automate generating recipes from Youtube cooking videos.

Leetcode grind - Remove duplicates from a sorted linked list

matej — Sun, 21 Nov 2021 14:52:29 +0000

This one is pretty simple if there is just one duplicate, but if there are multiple, using just one pointer won't work, because we need to skip multiple duplicates.

Going on solution from z3r0gravity7 from here https://leetcode.com/problems/remove-duplicates-from-sorted-list/discuss/1589369/Python3-intuitive-O(n)-solution-with-seeking-pointer-faster-than-98-(with-explanation) ->

def deleteDuplicates(self, head: Optional[ListNode]) -> Optional[ListNode]:
        if head == None or head.next == None: # handle edge cases where linked list has no or one nodes
            return head

        p = head # initialize current node pointer
        while p.next: # until we have reached the last node (where next pointer is None)
            seek = p.next # seek pointer is initialized to the node after current node (guaranteed to be not None by while loop condition)
            while p.val == seek.val: # while the seeking pointer points to a duplicate of the current node
                seek = seek.next # keep seeking
                if seek == None: # if the seeking pointer has reached the end of the LL
                    p.next = None # then all nodes after the current node are duplicates, can truncate the LL after the current node
                    return head

            # the seeking node is at the first non-duplicate node (may not have moved at all, if there were no duplicates)
            p.next = seek # skip over all duplicate nodes (if any) by forwarding the next pointer of the current node to the seeked to node
            p = p.next

        return head

We can make it a bit more readable using suggestions from Elements of Programming interviews, and then we get:

    def deleteDuplicates(self, head: Optional[ListNode]) -> Optional[ListNode]:
        first = head

        while first:
            second = first.next
            while second and first.val == second.val:
                second = second.next
            # skip over all duplicate nodes
            first.next = second
            first = first.next

        return head

In the end it's kinda simple.

As usual it's really best to just work out the whole thing on paper, code will just get in the way.

I'm new to the grind, the hardest thing so far is to just stick to it.

DEV Community: matej

Remixing songs using Chat GPT-4 and the command line

Leetcode grind - Remove duplicates from a sorted linked list