Get the BEST AI Voice Models by Analyzing Tensorboard for RVC

แชร์
ฝัง
  • เผยแพร่เมื่อ 2 ธ.ค. 2024

ความคิดเห็น • 115

  • @DogeDraws
    @DogeDraws ปีที่แล้ว +2

    So hyped for the dataset analysis video man, keep it up!

  • @TheNoobyworld
    @TheNoobyworld ปีที่แล้ว +4

    6:20 This isn't actually necessary.
    To save more logs to the tensorboard you can change the setting in configs/48k_v2.json (or the Json of the model type you selected when creating) and edit "log_interval" down from 200 to 25 steps to save the loss to tensorboard more often without needing to save the model state at all.

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว +1

      Good tip, but the purpose I was going for wasn't for logging, it was for having the model to use. You can check the logs to find a good spot, but if you don't have the model at that point... Well you gotta retrain it lol.

  • @fuuka69420
    @fuuka69420 ปีที่แล้ว +6

    Once again a great tutorial on Ai/Deeplearning wrapped in a really easy for end user to understand!
    Also, I notice some of the EN Holo members talked about your video in one of their stream which is pretty cool, maybe this is a question for your Q&A session next time. what are your thought on one of your videos getting their attention and how do you feel about their reaction to it? Keep at it mate and I can't wait for your next videos!

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว +4

      Appreciate it! I'm glad to hear that my content is resonating with you :)!
      As for their reaction to my videos, it's always intriguing to see how different people respond to the technology I discuss, esp large streamers. I knew sooner or later they would come across it and it's intriguing to hear their POV on this topic. Is it Watson?

    • @fuuka69420
      @fuuka69420 ปีที่แล้ว

      @@Jarods_Journey True true! I guess if its streamers they'll have mix reaction regarding this AI stuff as I think influencer such as them will be the first one to be copied. and yes haha right on the money mate 😄✨

  • @brucejsg
    @brucejsg ปีที่แล้ว +3

    Sorry for the dumb question, but which one of the lines (vertical/horizontal) in thosebgraphs represents my epoch ? How did you which epoch was when you made your comparison with the 70k model ?

  • @hungisbetter7948
    @hungisbetter7948 ปีที่แล้ว +2

    Dear TH-cam channel owner,
    I am a fan of your channel and regularly watch your videos with great enthusiasm. I really admire how you use background music in your videos, which makes each video more vibrant and engaging.
    Indeed, I have been searching and would like to know the list of background music used in some recent videos on your channel.

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว +1

      All belong to and are created by a Japanese artist, しゃろう

    • @hungisbetter7948
      @hungisbetter7948 ปีที่แล้ว

      @@Jarods_Journey Thanks you so much

  • @bomar920
    @bomar920 ปีที่แล้ว +2

    I hope they will be upgraded voice cloning of RVC . This current one is nice but looking forward next generation

  • @HBMHD
    @HBMHD 9 หลายเดือนก่อน +6

    What's the difference between Epoch and steps? My models sounds TERRIBLE (noisy, robotic, staticky) with 40 minutes of super clean and crisp datasets at 200 Epochs and 18,600 steps... Is that amount of steps normal for 200 Epochs?

    • @arhamahmedkhan7060
      @arhamahmedkhan7060 หลายเดือนก่อน

      When I tried training in mangio, my model also sounded terrible. So I used Applio which is better

  • @basspig
    @basspig ปีที่แล้ว +2

    I just do 250 epochs and consider it done.

  • @vixxcelacea2778
    @vixxcelacea2778 9 หลายเดือนก่อน +2

    For those of us with crappy or no GPU who have been using google colab to make models, KIts AI has an upload feature for .pth and index. It allows for free generation of audio it has, which includes singing and talking. You can also upload up to 15 minutes of your own audio bites, but I use the free generation to check as it doesn't use the limitation for free accounts.
    I have also reused decent singing samples generated from voice back into my dataset for the model to train it to sing certain notes or just sing in general along with all the talking data I have for each.
    I've made 8 character models and I can tell that they sound like them with the singing and talking free samples Kits AI allows. You can upload lots of models at once and run them all in the same sample. I've compared different epoch points this way too with the same model or different data sets.
    It's faster than RVC in some cases and allows me to test singing specifically with out having RVC use my CPU to generate input.

  • @Timur-u5z
    @Timur-u5z 11 หลายเดือนก่อน

    why does No dashboards are active for the current data set. appear? I have trained model and if it looking for index file inside the logs folder i have one

  • @pokepress
    @pokepress ปีที่แล้ว

    Can you explain mathematically what the graph is showing? It looks like it’s a ratio between different numbers, but I can’t tell which numbers they are.

  • @Suddenamboush
    @Suddenamboush 6 วันที่ผ่านมา

    I could do it yesterday, today I get errno13; no permission. What am I doing wrong? help please

  • @Nanaten
    @Nanaten ปีที่แล้ว

    How do I get tensorboard on the google colab version?
    Everytime, I get an error code and it won't show up

  • @osxty9
    @osxty9 7 หลายเดือนก่อน

    what do you mean by overtraining? do you mean more epochs or more new datasets fed in the pre trained model ..Sorry for my bad English ❤

  • @thecysserofan
    @thecysserofan ปีที่แล้ว

    When I do the venv Scripts activate and hit enter I get "Cannot be loaded because running scripts is disabled on this system" Help

  • @carterkovac
    @carterkovac ปีที่แล้ว +1

    hey jarod, thanks for all the videos! i was wondering if you can make a video on how to set it up on roblox, cs:go, val, etc. bceause it isn't seeming to work.

  • @YishayRaziel
    @YishayRaziel ปีที่แล้ว +1

    Great video!
    1. Can you explain for once the importance of an index file?
    I literally can’t hear the difference.
    2. Can I regenerate an index file if I have only the pth file?
    Thanks!
    You have amazing RVC content.

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว +1

      Index aims to keep more features of the voice, so it can help it maintaining accents. I can usually barely hear the difference as well.
      You need all the audio training data for the index file unfortunately, not the pth

  • @Maposil
    @Maposil ปีที่แล้ว +1

    How can i unistall AI Voice Changer ?

  • @SK-hj1xh
    @SK-hj1xh ปีที่แล้ว

    Hi. How train above 1000 Total training epochs. If I put some bigger number it returns max 1000 epoch.

  • @brucejsg
    @brucejsg ปีที่แล้ว

    Is there a way to conitnue training from the last epoch i stopped ? Lets say in another day after i already closed the app. Thank you

  • @AICoverMaster-yi6kf
    @AICoverMaster-yi6kf 7 หลายเดือนก่อน

    Sir Jarod, do you have a video on hyperparameters?

  • @InspiroVibz
    @InspiroVibz ปีที่แล้ว

    Hi, i set up save frequency at 50 and every 50 epochs it create 2 different pth files one called G_"epochnumber".pth and another one d_"epochnumber".pth
    when i try to load any one of them to test it out i've got an error.
    Did you have them automatically loaded into ur voice models .pth list?
    thanks!

  • @AlfRentgen
    @AlfRentgen ปีที่แล้ว

    Hi Jarod! What are the duration of WAV files in 0_gt_wavs and 1_16k_wavs directories after the step 2a? Mine are 3 seconds long. I have quite clean data set, 3 hour long. But it seems that the loss_mel stuck somewhere at 20 after 120 epoches. And the generated voice sounds a bit synthetic.

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว +1

      I often see that longer datasets may not be necessary, I would try with an hour dataset to make training a bit faster, and then try training for longer. The files in folder 0 and 1 and from the preprocess step and will be cut to around 3 seconds for RVC to process.
      Synthetic may depend on what you're trying to inference on, so try other audio files to see if that could be the case here too.

  • @BigLoafJae19
    @BigLoafJae19 ปีที่แล้ว

    on RVC is the houshou Marine voice alr available?

  • @xZaktor21
    @xZaktor21 ปีที่แล้ว +2

    Good video!! I like your content about rcv (although I don't know python lol). Which would you say is the best extraction algorithm between harvest, crepe and magio crepe? (I have a good dataset only spoken but I would like to use the AI to do covers)

    • @blakusp
      @blakusp ปีที่แล้ว +1

      if spoken dataset: preprocess with harvest (best for speak) and later inference with mangio-crepe

    • @nxrthsidebxy
      @nxrthsidebxy ปีที่แล้ว +1

      @@blakusp what if singing dataset? what the best option for that

    • @blakusp
      @blakusp ปีที่แล้ว +1

      @@nxrthsidebxy mangio-crepe for sure

    • @amiraskari4055
      @amiraskari4055 ปีที่แล้ว

      what about rvmpe? @@blakusp

  • @denblindedjaligator5300
    @denblindedjaligator5300 5 หลายเดือนก่อน

    what do you meen by steps?

  • @rodrigo.damasceno
    @rodrigo.damasceno ปีที่แล้ว

    Hi Jarods! You can make a tutorial about using RVC without interface? using prompt comands! Because im trying integrade RVC to my pyton code! text to speak default and default to RVC. thanks

  • @BrennerEraFan
    @BrennerEraFan ปีที่แล้ว

    Is over training bad quality wise?

  • @jayr7741
    @jayr7741 ปีที่แล้ว

    I want to create audiobook with my clone voice for free is there anything to do it? Plz reply

  • @jerrythefeared
    @jerrythefeared ปีที่แล้ว +1

    Hey Jarod, great video! One question though, from what folder did you take the models from step 10k and 70k?

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว

      Rvc folder, the weights folder

    • @jerrythefeared
      @jerrythefeared ปีที่แล้ว

      Only my final version is in there, what about the versions in between?

    • @5b454
      @5b454 ปีที่แล้ว

      @@jerrythefeared should be in drive under, rvc_backup -> weights -> in the format of 'modelname_e[epochnumber]_s[stepnumber].pth

    • @nickvilliers5216
      @nickvilliers5216 ปีที่แล้ว

      I think you just have to train more epochs to get higher step counts in the network, thus potentially improving neural network performance (though not always). The number of individual steps (parameter updates) in an epoch depends on the dataset size. For example, with a dataset of 10,000 images and a batch size of 100, each epoch would have 100 steps.

  • @TheThornmir
    @TheThornmir ปีที่แล้ว

    Hi, do you know if the model created with RVC can be reused with other clients for text to speech for example ? In onnx format ?

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว

      No, tts is a completely different architecture and atm, I don't know of any that convert to each other.

  • @innutshell81
    @innutshell81 ปีที่แล้ว

    Hello I have a question and I cannot find any solution for this. I have 1277 around 5s wav files for training. On my RTX 3080 it took 13 hours to generate 10 epochs, using 26 batch size. Is it normal for it to take so long with this dataset? I want to train on total 200 epochs, how do I go about it then? On collab, one epoch on the same dataset took few minutes, but I cant use it because the notebook will still terminate to early. I then used a dataset with 200 files but it still took verylong, on 20 files one epoch took mabye 5 mins? I honestly dont know what is the issue.

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว

      Odd, you might wanna increase your batch size. That comes out to less than 2 hours of audio for the whole dataset... So at most I would assume it be closer to maybe 10 minutes per epoch.
      Make sure you have torch installed correctly on your system

  • @tunafizzle1
    @tunafizzle1 ปีที่แล้ว +1

    Have you played with mangio crepe v2 at all? I was running it on colab and it had tensorboard built in. It seems like everybody is using it now but I don't know that I was getting much better/faster results. Just curious if you haven't gotten around to messing with it or if you think RVC v1 is better.
    Thanks for the videos, very helpful!

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว +1

      I haven't gotten around to mangios V2 but a lot of people recommend it! I will test it out sometime so until then

    • @taoleee
      @taoleee ปีที่แล้ว

      @@Jarods_Journey you need to delete and reinstall the latest mangio rvc. I did a git pull and mangio crepe didn't show up.

  • @BlueprintBro
    @BlueprintBro ปีที่แล้ว

    Your videos are 10/10

  • @BoahsLoL
    @BoahsLoL 11 หลายเดือนก่อน

    if I've trained a model for 1,000 steps can I train it again for 1,000 more after it's finished? It seems 1,000 is the max with RVC to do at one time.

    • @Jarods_Journey
      @Jarods_Journey  11 หลายเดือนก่อน +1

      RVC's max is 1000. You can try download mangios RVC which allows you to train longer I believe.
      The only way to enable it in RVC is the manually edit the parameter in the Gradio code.

  • @linuxtuxvolds5917
    @linuxtuxvolds5917 ปีที่แล้ว

    Thank you, Jarod! ♥

  • @davy4842
    @davy4842 ปีที่แล้ว

    Hi can you mix between several models ?

  • @ItsMeCharkey
    @ItsMeCharkey ปีที่แล้ว

    For mine it just said NaN on both the smoothed and Value things, how would I change that?

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว

      Something may have occured during training... Though idk what. You may have to run training again under a different experiment name to get the train graphs

  • @luciovids9208
    @luciovids9208 ปีที่แล้ว +1

    Hey Jarod, how about a tutorial on creating deepfake or deepface or faceswap videos? I think you could show us how to do it better than others. Thanks

  • @LucidFirAI
    @LucidFirAI ปีที่แล้ว

    Wait so, can I be watching this tensorboard in realtime to save time and stop training when it flatlines?
    Can you ELI5 a simple rule of thumb for choosing how many epochs to train at? I've got a tensorboard graph that goes down to 10k and then starts rising again from 25k to 40k...

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว +1

      There's no rule for epoch count because all datasets are different. You may converge faster on one compared to another. Its pretty much a game of just looking at your training and making speculations on what the best stopping point is going to be

    • @LucidFirAI
      @LucidFirAI ปีที่แล้ว

      @@Jarods_Journey Good to know, thanks.
      Do you have a discord server at all? There are discords for basically everything but I can't find one for local TTS.

  • @hyeonoppa
    @hyeonoppa ปีที่แล้ว

    When are you testing, are you referencing the index file at all? Is it really needed?

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว +2

      index is not needed for good quality, it mainly just affects how close of an accent the voice has.

  • @archidoubi
    @archidoubi ปีที่แล้ว

    Hi Jarod, thanks for all the good work. I trained for 10000 epochs and checkpointed every 50 epochs and I have not even one model which is low on the graph, they're all on "high" points of the graph. What can I do to get the best one :/ ?

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว +2

      You could try saving more often so you can get one to save at a valley, but I just recommend you pick one and listen to it. Graph numbers don't really mean much, just as long as it was going down it should be fine in most cases.

  • @TrunxKraft3000
    @TrunxKraft3000 10 หลายเดือนก่อน

    Once i train a model, how can i make it available to my customers?

    • @Jarods_Journey
      @Jarods_Journey  10 หลายเดือนก่อน

      Well, most likely you'll want to host it somewhere and then allow you're customers to select a voice and use it. Either that, or you can distribute the model to them... though that would most likely be too cumbersome I'd assume.

  • @SparkysTechCorner
    @SparkysTechCorner ปีที่แล้ว

    Very informative, thanks for the info

  • @Hunlor-
    @Hunlor- ปีที่แล้ว

    Bro my Buffer is really high and increasing a lot the response time, i've noticed yours stays almost at 0. How do i fix this?

  • @ItsMeCharkey
    @ItsMeCharkey ปีที่แล้ว

    What’s a good way to know what octave the training data is in?

  • @OwOMashiro
    @OwOMashiro ปีที่แล้ว

    Hey there is there any guide to download the ai soundboard? im kinda new to this thing

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว +1

      Not sure what the AI soundboard is, but no guide on my channel

    • @OwOMashiro
      @OwOMashiro ปีที่แล้ว

      @@Jarods_Journey ah okay!

  • @Tom_Neverwinter
    @Tom_Neverwinter 4 หลายเดือนก่อน

    feels like you can find rvc models but now none of the programs work to train new models

  • @Mariano_art
    @Mariano_art ปีที่แล้ว +2

    you are the best !!!

  • @TheChipMcDonald
    @TheChipMcDonald ปีที่แล้ว

    Good job.... but now I'm hearing about rvmpe...?

  • @sinhaplaban
    @sinhaplaban ปีที่แล้ว

    Similar approach I can use in Collab as well right?

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว

      Yup, you can run tensorboard in Collab if you want buy youll have to find the code to do that somewhere out there

  • @SplicerTv
    @SplicerTv ปีที่แล้ว +2

    This is super useful, but for some reason my tensorboard graph does not look as detailed as the one you have. I trained for 200 epochs and checkpointed every 20 epochs, but I am not seeing the graphs plot with that many points I only see about 2 - 3 points (very simplified) vs. what you're seeing with lots of points for each step. I made a fresh conda environment with python 3.9 and latest tensorboard and followed your steps. Any advice?

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว +1

      I did one at every epoch lol, that's why. For video purposes only, I don't recommend you do this as it increases the total training time.

  • @MaisnerProductions
    @MaisnerProductions ปีที่แล้ว

    great stuff!

  • @whitegoose-k4g
    @whitegoose-k4g ปีที่แล้ว

    help, my 6GB 3060 out of VRAm. can i fix that? or should i just cry?

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว

      Lower batch size or make sure dataset samples are all 10 seconds or less, other than that, that may be too small to run this nicely

    • @whitegoose-k4g
      @whitegoose-k4g ปีที่แล้ว

      @@Jarods_Journey stupid question, i have 3 hours worth of clean and crisp audio recording. if i cut that off and have like 10 seconds and make like 1000 files, do i need to train it one by one. or can i just precess it once?
      thanks for the reply

    • @tiborvarga5391
      @tiborvarga5391 ปีที่แล้ว

      @@whitegoose-k4g You can load all files into a folder after chopping it up and that will be processed. The more audio you have the slower it will run. Also you will need to lower your batch size significantly.
      It is useful to chop up the data, so it can be loaded and buffered in smaller chunks. Cmaller chunks provide more felxibility in loading in the data allowing the buffer to be as close to full as possible.

  • @dopaminejuice
    @dopaminejuice ปีที่แล้ว

    What's the difference between RVC v1 and RVC v2?

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว +1

      They describe V2 as using a "768 dimensional feauture of 12 layer hubert" which means that it can perhaps capture more feautres of the voice due to the dimension of the vector being larger and training through more layers to hopefully learn the complexities of the voice better.

  • @ImInTheMaking
    @ImInTheMaking ปีที่แล้ว

    how do you create an executable for the tensorboard instead of always typing it manually under vs code?

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว +1

      ChatGPT it :), that's what I would do. Should just be a few line

  • @xperrttt
    @xperrttt ปีที่แล้ว

    wallpaper link?

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว

      You can probably find it easily by looking up rem landscape wallpapers lol, I don't have an exact link

  • @knmohitkumar7332
    @knmohitkumar7332 ปีที่แล้ว

    Can we increase the limit of epoch numbers from 1000 to more in offline training. If yes then please guide me. Thank you🙂

  • @gabriel.a.f.parker7291
    @gabriel.a.f.parker7291 ปีที่แล้ว

    man, we arrived in cyberpunk

  • @Sensei_07-sea
    @Sensei_07-sea ปีที่แล้ว

    Tks you!

  • @dougmaisner
    @dougmaisner ปีที่แล้ว

    very useful

  • @kevinscales
    @kevinscales ปีที่แล้ว

    I just get 'NaN' when training and can't get a clear voice like others get.

    • @hipete1295
      @hipete1295 ปีที่แล้ว

      Maybe try setting the learning rate lower? You would have to edit the config file in the configs folder

    • @AlfRentgen
      @AlfRentgen ปีที่แล้ว

      What GPU do you use? I had the same issue on my 1660, fixed it myself. And reported on the github.

  • @RobertJene
    @RobertJene ปีที่แล้ว +1

    [overtrains it on purpose for the lols]

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว +1

      Could be the voice affect your going for lool 👀

  • @zap0p3rr0tr3inta
    @zap0p3rr0tr3inta 10 หลายเดือนก่อน

    3:11

  • @Mowgi
    @Mowgi ปีที่แล้ว

    croissant

  • @michaz9608
    @michaz9608 8 หลายเดือนก่อน

    jesus, why so complicated

  • @_nom_
    @_nom_ ปีที่แล้ว

    Python is a terrible language with a terrible platform, yikes.

  • @knmohitkumar7332
    @knmohitkumar7332 ปีที่แล้ว +1

    Can we increase the limit of epoch numbers from 1000 to more in offline training. If yes then please guide me. Thank you🙂

    • @Jarods_Journey
      @Jarods_Journey  ปีที่แล้ว

      1k is the max for base RVC :)!

    • @knmohitkumar7332
      @knmohitkumar7332 ปีที่แล้ว +1

      @@Jarods_Journey then how can i increase it. Do you have any clue? Is there any other version of rvc their which supports epoch beyond 1k.

    • @hipete1295
      @hipete1295 ปีที่แล้ว

      Hey, in the gradio page, use inspect elements, change the max value when the epoch slider is selected. Do it for both the slider and the number box.

    • @knmohitkumar7332
      @knmohitkumar7332 ปีที่แล้ว

      @@hipete1295 i've tried this. But no luck. I'll try again with hope.

    • @knmohitkumar7332
      @knmohitkumar7332 ปีที่แล้ว +1

      I found the way bro.