hey , tnx for the video , i have a problem with code , why 'tokenizer' has None value and None Type ? i checked code on github and saw same problem there.
Just after installing !pip install transformers you need to install !pip install sentencepiece before importing the PegasusTokenizer......... i hope this helps :)
why am i getting error when i import the model from transformers import PegasusForConditionalGeneration, PegasusTokenizer >>> import torch AttributeError: 'Version' object has no attribute 'major' pls help
i got thi error :'NoneType' object is not callable (on this code (model_name = 'google/pegasus-large' torch_device = 'cuda' if torch.cuda.is_available() else 'cpu' in this line (((tokenizer = PegasusTokenizer.from_pretrained (model_name) please help me
@@RitheshSreenivasan Thank you for the video and the script it has been a great help. Just one question, if I have my own dateset (which is TFDS) on my local pc all i have to do is replace it with el xsum in the script and adjust batch size and epochs?
@@RitheshSreenivasan with your help and refrence I was able to fine-tune the model, but i'm stuck on implementing it like you have in the video. I don't know how to turn it into a format which I can use to give it an input and have an output.
Do you mean to code to fine-tune on your documents. I have not explored it as of yet. The code i have used in this example is available here:github.com/rsreetech/PegasusDemo
Not exactly as here the text summary is generated . In extractive you just extract relevant sentences as is from the text. In some cases yes the results look very much like extractive and in some cases they look like they have been generated
RUclips's automatic translation is very very bad, perhaps your pronunciation too, although I understood more by listening than by reading the ramblings that it generated as a translation. I encourage you to practice your pronunciation, or to translate it with whisper, so that you can see for yourself if it makes sense or not, things like "transformers of the porn border" came out. so imagine.
To fix the issue replace the batch variable to :
batch = tokenizer(src_text, truncation=True, padding='longest', return_tensors='pt').to(torch_device)
Which issue are you talking about
@@RitheshSreenivasan github.com/huggingface/transformers/issues/8691
@@RitheshSreenivasan I sent you also a question on email, I would like you to answer :)
@@doric1111 please can you tell me how you resolve this issue
Nice explanation!
Thank you!!
nice explanination
Thank you!
can you implement,
how to evaluate abstractive summarization.
thanks
Unless you have some ground truth summary evaluation is difficult. If there is ground truth the you can evaluate using Bert score, rouge metrics
@@RitheshSreenivasan
Thanks !
ground truth summary you mean human generated summary which is also called the reference?
Yes
@@RitheshSreenivasan
Thanks for your time.
Great Content.
Thank You!! I will try
please tell me how we increase the length of the summary
Have a look at Pegasus documentation
Do this support for indian languages
No this model does not support Indian languages
Great video! Have you considered using GPT-2 or GPT-3 for this task?
I have not as of yet. But would be interested in looking at GPT-2 or GPT-3
hey,
can you help how to evaluate abstractive summary generated using gpt3.
✌
Is there a way to increase length of summary? I mean, is there a parameter that can be tuned to increase summary lengths?
Have a look at Pegasus documentation
Did you figure out how to increase the summary lengths?
Is it possible to apply the model for other Indian languages?
No it works for English
@@RitheshSreenivasan how it can be implemented for other languages? We have any option to train the same model with other language dataset?
Follow the paper
hey , tnx for the video ,
i have a problem with code , why 'tokenizer' has None value and None Type ? i checked code on github and saw same problem there.
Could be an issue with how transformers library is installed
Just after installing !pip install transformers you need to install !pip install sentencepiece before importing the PegasusTokenizer.........
i hope this helps :)
and use this code to tokenize:
batch = tokenizer(src_text, truncation=True, padding='longest', return_tensors='pt').to(torch_device)
why am i getting error when i import the model
from transformers import PegasusForConditionalGeneration, PegasusTokenizer
>>> import torch
AttributeError: 'Version' object has no attribute 'major' pls help
Seems to be an issue with PyTorch installation.
Can you share any link to install torch properly
@@Manideep. You can go to the official page of pytorch . I had followed the instructions from there
How can we extend the same over meetings?
Can you elaborate your use case?
@@RitheshSreenivasan I was trying to generate minutes of meeting for meetings with multiple participants.
You are better off with some custom NLP algorithm which can identify participants first followed by detection of important points
i got thi error :'NoneType' object is not callable
(on this code
(model_name = 'google/pegasus-large'
torch_device = 'cuda' if torch.cuda.is_available() else 'cpu'
in this line (((tokenizer = PegasusTokenizer.from_pretrained (model_name) please help me
Not sure about the error
Hi sir can we able to max or min the length of summary. 🤔
Look at hugging face Pegasus documentation. I have not experimented on length of summary
@@RitheshSreenivasan thanks sir 😊
How can I fine-tune the PEGASUS large checkpoint?
gist.github.com/jiahao87/50cec29725824da7ff6dd9314b53c4b3
@@RitheshSreenivasan Thank you for the video and the script it has been a great help. Just one question, if I have my own dateset (which is TFDS) on my local pc all i have to do is replace it with el xsum in the script and adjust batch size and epochs?
Should work
@@RitheshSreenivasan with your help and refrence I was able to fine-tune the model, but i'm stuck on implementing it like you have in the video. I don't know how to turn it into a format which I can use to give it an input and have an output.
do you have source code using hugging face of pegasus to do summarization task ?
Do you mean to code to fine-tune on your documents. I have not explored it as of yet. The code i have used in this example is available here:github.com/rsreetech/PegasusDemo
aren't these results more like extractive ?
Not exactly as here the text summary is generated . In extractive you just extract relevant sentences as is from the text. In some cases yes the results look very much like extractive and in some cases they look like they have been generated
RUclips's automatic translation is very very bad, perhaps your pronunciation too, although I understood more by listening than by reading the ramblings that it generated as a translation. I encourage you to practice your pronunciation, or to translate it with whisper, so that you can see for yourself if it makes sense or not, things like "transformers of the porn border" came out. so imagine.
Can’t help if RUclips’s automatic translation is broken. If you can’t understand my pronunciation don’t watch the videos