Quality of outputs.

[rajdeep-biswas]

1. Resumes that have 'questionable' encodings give the model some trouble and produce garbage output.

2. Long (text-heavy) resumes error out the model.
   Token indices sequence length is longer than the specified maximum sequence length for this model (7098 > 1024). Running this sequence through the model will result in indexing errors [2021-08-20 12:40:26,584] ERROR in app: Exception on / [POST]
   ... Traceback ...
   IndexError: index out of range in self

3. Shorter resumes produce following warning, even though the origin of these numbers specifying min/max length are not known.
   Your min_length is set to 56, but you input_length is only 3. You might consider decreasing min_length manually, e.g. summarizer('...', min_length=10) Your max_length is set to 142, but you input_length is only 3. You might consider decreasing max_length manually, e.g. summarizer('...', max_length=50)