saarthdeshpande/book-summarizer

Using pretrained T5 model for abstractive summarization of books

book-summarizer's Issues

During installation - Could not find ginger it version

See ERROR: Could not find a version that satisfies the requirement gingerit==0.8.0 (from versions: none)
ERROR: No matching distribution found for gingerit==0.8.0

KeyError and smtplib.SMTPAuthenticationError

'Corrections'
Traceback (most recent call last):
File "/content/book-summarizer/model.py", line 107, in summaryGeneration
summary = sentenceCorrection(summary)
File "/content/book-summarizer/model.py", line 43, in sentenceCorrection
sentenceDict = parser.parse(sentence)
File "/usr/local/lib/python3.7/dist-packages/gingerit/gingerit.py", line 27, in parse
return self._process_data(text, data)
File "/usr/local/lib/python3.7/dist-packages/gingerit/gingerit.py", line 39, in _process_data
for suggestion in reversed(data['Corrections']):
KeyError: 'Corrections'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "bsCLI.py", line 20, in
pdfParser(app.config['PDF_UPLOADS'] + '/pdf_file.pdf')
File "/content/book-summarizer/preprocess.py", line 96, in pdfParser
splitChapters(filename, mailid)
File "/content/book-summarizer/preprocess.py", line 75, in splitChapters
summaryGeneration(mailid)
File "/content/book-summarizer/model.py", line 120, in summaryGeneration
send_fail(mailid)
File "/content/book-summarizer/mail.py", line 17, in send_fail
session.login(sender_address, sender_pass) # login with mail_id and password
File "/usr/lib/python3.7/smtplib.py", line 730, in login
raise last_exception
File "/usr/lib/python3.7/smtplib.py", line 721, in login
initial_response_ok=initial_response_ok)
File "/usr/lib/python3.7/smtplib.py", line 642, in auth
raise SMTPAuthenticationError(code, resp)
smtplib.SMTPAuthenticationError: (535, b'5.7.8 Username and Password not accepted. Learn more at\n5.7.8 https://support.google.com/mail/?p=BadCredentials v64sm11061838pfc.117 - gsmtp')

importation error

ImportError:
T5Tokenizer requires the SentencePiece library but it was not found in your environment. Checkout the instructions on the
installation page of its repo: https://github.com/google/sentencepiece#installation and follow the ones
that match your environment.

I have checked on the readme I didn't see anything relating to token except when you were explaining the project.

Token indices sequence length is longer than the specified maximum sequence length for this model

Converting PDF to txt file.
Successfully converted PDF to txt.
Total Number of Lines: 13596
No chapters in book! Writing entire book!
Done writing!
pdf_fileChapterAll.txt
Summarising: pdf_fileChapterAll.txt
Token indices sequence length is longer than the specified maximum sequence length for this model (536 > 512). Running this sequence through the model will result in indexing errors

FileNotFoundError: [Errno 2] No such file or directory: 'static/pdf/uploads/pdf_file.pdf'

Traceback (most recent call last):
File "/content/book-summarizer/bsCLI.py", line 19, in
copyfile(args.path, app.config['PDF_UPLOADS'] + '/pdf_file.pdf')
File "/usr/lib/python3.7/shutil.py", line 121, in copyfile
with open(dst, 'wb') as fdst:
FileNotFoundError: [Errno 2] No such file or directory: 'static/pdf/uploads/pdf_file.pdf'

Errors on Step 2 and 3

Ok, I am getting errors. Let me know what I can do. Thank you!