@abhishekkrthakur , at 12:28, you told to clone the bark repo. But, I could not find the exact bark repo which you have shown. Can you provide the link for the bark repo? Please
I am struggling with this..i dont relize how the bark folder come? I saw in the bark repo there is no speaker embedding..can you please give me this full code or steps which i can follow?
I am having one problem with input context length. For example given a research paper, I am trying to find relevant papers from the vector db containing 2000 papers. How to fit the entire research paper as the input? Is there any way to solve the problem? Also the vector db is huge. Is there any way to manage it efficiently?
In duration of 12:25 you sad clone the repo , but i don't know exact repo where it is ,can yu share the link of repo, because if go and donwload each file one by one, it's hard, especially in speaker_embedding multiple files are there
I have a tts read it outloud and it takes a bit to hear the tts after clicking start code.. is there a way to make it faster? you kinda get them very fast or something i have no coding experience and yours is just in another code file mine plays the sound from media player (it have to) + if text are long he reads only 14 seconds of it.. it just take sooooooooooooo long is that normal??
Ok, so a bit new to all this, but can you tell me what repositories you used in your bark folder? The script is missing stuff and not sure what. Thank you.
Hi Sir, humble request, can you please share your journey of being kaggle grandmaster and guide the juniors out here. If you already have posted somewhere, would love to have link to it. 😁
HI Abhishek. Thanks for posting some interesting videos. I tried doing text to speech using Bark on V100 GPU on Bark. It is taking too long. I need latency of less than a second. Can you recommend how I could achieve that.
Please subscribe to help me keep motivated to make awesome videos like this one. :)
Cool tutorial bhaiya 😌🙌
Would you take up small duration text-to-video in the next tutorial?
You're the one sir, I just love your videos and you're a big motivation for all us wannabe pro. I follow you on twitter and youtube!
Hello! Could I contact you please? I urgely need your help with my Diploma thesis work. Please
Nice Abhishek
Hey Abhishek, can we clone our own voice using this, if so can you please make a video to educate us. Great content.
Abhishek I have been following your videos and tutorials for last 2 years. Your content was and is gold!
Hi bro, how did you make that your youtube profile photo ? Can you guide me ?
@abhishekkrthakur , at 12:28, you told to clone the bark repo. But, I could not find the exact bark repo which you have shown. Can you provide the link for the bark repo? Please
did u find it?
@@sabeerfaisal2619 go to the huggingface model repo for bark, there is a command "clone the repo".
UnpicklingError: invalid load key, '
I got the same issue, did you figure out how to fix it?
i have figure out, u wanna know...
@@tarangsuri8932 yes please
@@tarangsuri8932 I wanna know bro. Help me for solving this issue
@@tarangsuri8932 batade bhai abhi... secret rakhane wala he kya?🤣
Does the quality of the generations increase if you have longer or more samples?
Where's your next video! Your channel always inspires me!!!! Cant wait to watch your new video
Thank you for your kind words. Ive taken a break from making videos 🙂
@@abhishekkrthakur Oh, it's a pity!!! Still wish everything goes well with your life
I am struggling with this..i dont relize how the bark folder come?
I saw in the bark repo there is no speaker embedding..can you please give me this full code or steps which i can follow?
now, did this work?
12:20 Clone which repository?
hf.co/suno/bark
I am having one problem with input context length. For example given a research paper, I am trying to find relevant papers from the vector db containing 2000 papers. How to fit the entire research paper as the input? Is there any way to solve the problem? Also the vector db is huge. Is there any way to manage it efficiently?
In duration of 12:25 you sad clone the repo , but i don't know exact repo where it is ,can yu share the link of repo, because if go and donwload each file one by one, it's hard, especially in speaker_embedding multiple files are there
can someone tell me where is the bark repository?, which was used and shown at 12:28
magic_number = pickle_module.load(f, **pickle_load_args)
_pickle.UnpicklingError: invalid load key, '
yep, that ain't working
im also facing issue
same issue, any updates ?
Same issue here
Same issue. Has anyone been able to solve it??
bro please do mention the links also in the descriptions
Thanks for the video, I was looking for this recently. I am too shy to talk for youtube videos was hoping to clone my voice like this for one.
Nice tutorial Abhishek!
Hi Abhishek, I really like your book, thank you so much for sharing your knowledge.
I have a tts read it outloud and it takes a bit to hear the tts after clicking start code.. is there a way to make it faster? you kinda get them very fast or something i have no coding experience and yours is just in another code file mine plays the sound from media player (it have to) + if text are long he reads only 14 seconds of it.. it just take sooooooooooooo long is that normal??
Ok, so a bit new to all this, but can you tell me what repositories you used in your bark folder? The script is missing stuff and not sure what. Thank you.
same issue
Awesome. Video generation for the next one!
hi, I just found out about your AAAML book, but cant find the code repo of it, could you please share it?
Hi Sir, humble request, can you please share your journey of being kaggle grandmaster and guide the juniors out here. If you already have posted somewhere, would love to have link to it. 😁
How do you fine tune MMS-TTS models?
HI Abhishek. Thanks for posting some interesting videos. I tried doing text to speech using Bark on V100 GPU on Bark. It is taking too long. I need latency of less than a second. Can you recommend how I could achieve that.
For my personal questions, can you share your method of learning something new. I really don't have method to learn data industry
Hello thank you bro
Where is bark folder
I want to clone my voice in german but it has everytime a englisch pronounce how can i set the language to german?
Requesting new videos!!!
Great Stuff! always. Thanks. Does Bark work on Apple silicon?
yes, just have to change device to cpu or mps
Possible to have your wav sample you use for the voice cloning ?
Can we generate long videos like 5 to 10 min
please mention the computing power required
AssertionError: Torch not compiled with CUDA enabled does someone know hat this is
same error as well, did yeah get it fixed?
Uninstall torch and reinstall it with pytorch documetation@@ashwinmlk4908
@@monilsompura H.O.W
Great video Abhishek, How can we develop our own text to speech model , it would give 3 mins of wav.file
You're amazing 🤩
Great video Abhishek. Can you possibly do a video on training a multitasking model in a computer vision setting? Would love to see that.
can i change the pitch and speed of the voice in bark?
were you able to get an answer ?
Great vid
how are you able to play audio in vs code?
you can open audio files in vs code by opening the folder in vs code and then you see them
nice video!
sad you don't provide the full code c/C...
Nice video
is there someone that has TTS problem? I did everything tho it doesn't seem to have TTS module
how to crack that issue
if you could just find a way to make this whole coding process thingy a copy and paste experience, that will just boom!
Can we try doing this with a phone?
hahaha
The echo in hindi is really cool
thats my mistake actually, but thanks 😃
Came here through Varun Mayya.
not working. also please attach codes it makes the process easier
good, but you so small in video
dont look at me. look at the code 😄
ngl it's like a light year away from ElevenLabs