Coder Social home page Coder Social logo

bedapudi6788 / deepcorrect Goto Github PK

View Code? Open in Web Editor NEW
129.0 5.0 33.0 33 KB

Text and Punctuation correction with Deep Learning

License: GNU General Public License v3.0

Python 100.00%
punctuation seq2seq correction text-correction grammar-correction txt2txt

deepcorrect's People

Contributors

bedapudi6788 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

deepcorrect's Issues

input shape error

1608 except errors.InvalidArgumentError as e:
1609 # Convert to ValueError for backwards compatibility.
-> 1610 raise ValueError(str(e))
1611
1612 return c_op

ValueError: Dimension 0 in both shapes must be equal, but are 2 and 98. Shapes are [2,256] and [98,256]. for 'Assign' (op: 'Assign') with input shapes: [2,256], [98,256].

Error in running the example.

After installing the TensorFlow version 1.14.0 and deepcorrect, I am running the example.
But I am getting the following error.

ValueError: Dimension 0 in both shapes must be equal, but are 2 and 98. Shapes are [2,256] and [98,256]. for 'Assign' (op: 'Assign') with input shapes: [2,256], [98,256].

Not compatible with TF 2.0

Hello,

I just wanted to tell you that this module is no longer working with the version 2.0 of TensorFlow.

I am getting the following error when importing:

AttributeError: module 'tensorflow' has no attribute 'set_random_seed'

The full traceback:

Traceback (most recent call last):
  File "<input>", line 1, in <module>
  File "/Applications/PyCharm CE with Anaconda plugin.app/Contents/helpers/pydev/_pydev_bundle/pydev_import_hook.py", line 21, in do_import
    module = self._system_import(name, *args, **kwargs)
  File "/anaconda3/envs/ziotag_metis_env/lib/python3.7/site-packages/deepcorrect/__init__.py", line 1, in <module>
    from .deepcorrect import DeepCorrect
  File "/Applications/PyCharm CE with Anaconda plugin.app/Contents/helpers/pydev/_pydev_bundle/pydev_import_hook.py", line 21, in do_import
    module = self._system_import(name, *args, **kwargs)
  File "/anaconda3/envs/ziotag_metis_env/lib/python3.7/site-packages/deepcorrect/deepcorrect.py", line 1, in <module>
    from txt2txt import build_model, infer
  File "/Applications/PyCharm CE with Anaconda plugin.app/Contents/helpers/pydev/_pydev_bundle/pydev_import_hook.py", line 21, in do_import
    module = self._system_import(name, *args, **kwargs)
  File "/anaconda3/envs/ziotag_metis_env/lib/python3.7/site-packages/txt2txt/__init__.py", line 3, in <module>
    from .txt2txt import *
  File "/Applications/PyCharm CE with Anaconda plugin.app/Contents/helpers/pydev/_pydev_bundle/pydev_import_hook.py", line 21, in do_import
    module = self._system_import(name, *args, **kwargs)
  File "/anaconda3/envs/ziotag_metis_env/lib/python3.7/site-packages/txt2txt/txt2txt.py", line 8, in <module>
    tf.set_random_seed(6788)
AttributeError: module 'tensorflow' has no attribute 'set_random_seed'

h5py error

https://colab.research.google.com/drive/10EcCIY91VjETzw_IYoLmajyrGvQrzZpB
You can run this codes.You will see this error:

OSError                                   Traceback (most recent call last)
<ipython-input-17-96cc841e4fb1> in <module>()
      1 from deepcorrect import DeepCorrect
----> 2 corrector = DeepCorrect('/content/sample_data/deeppunct_params_en', '/content/sample_data/deeppunct_checkpoint_wikipedia')
      3 corrector.correct('hey')

4 frames
/usr/local/lib/python3.6/dist-packages/h5py/_hl/files.py in make_fid(name, mode, userblock_size, fapl, fcpl, swmr)
    140         if swmr and swmr_support:
    141             flags |= h5f.ACC_SWMR_READ
--> 142         fid = h5f.open(name, flags, fapl=fapl)
    143     elif mode == 'r+':
    144         fid = h5f.open(name, h5f.ACC_RDWR, fapl=fapl)

h5py/_objects.pyx in h5py._objects.with_phil.wrapper()

h5py/_objects.pyx in h5py._objects.with_phil.wrapper()

h5py/h5f.pyx in h5py.h5f.open()

OSError: Unable to open file (truncated file: eof = 6291456, sblock->base_addr = 0, stored_eof = 10912808)

Help!

tfx support

I want to update or tutorial etc. for tensorflow serving.

Problem with reproducing results

Hi, I read your post https://medium.com/@praneethbedapudi/deepcorrection-3-spell-correction-and-simple-grammar-correction-d033a52bc11d and I am trying this pertained model with deeppunct_params_en and deeppunct_checkpoint_google_news/ deeppunct_checkpoint_tatoeba_cornell/ deeppunct_checkpoint_wikipedia respectively, however instead of getting:

INPUT: iwill be there four u
OUTPUT: I will be there for you.

I got:

INPUT: iwill be there four u
OUTPUT: Iwill be there four ?

Any suggestion to get result as good as yours?

Can't reproduce the same result as Demo

Hi, I can't reproduce the same result using the code as Demo

The system environment is Python 3.7.3, TensorFlow 1.14.0, txt2txt 1.0.9,

I used below parameter as it says in README.md, the params and checkpoint are download at https://drive.google.com/open?id=1Yd8cJaqfQkrJMbRVWIWtuyo4obTDYu-e

def __init__(self, params_path, checkpoint_path): DeepCorrect.deepcorrect_model = build_model("./deeppunct_params_en") DeepCorrect.deepcorrect_model[0].load_weights("./deeppunct_checkpoint_google_news")

I tried two sentence, the result comparison is as follow:

input: hey
my output: [{'sequence': 'Hey?', 'prob': 0.6868892775191712}]
Demo output: "deep-segment_punct": [
"Hey."
]

input: 'Why you did this to me I hate you you are dead to me'
my output: [{'sequence': 'Why you did this to me I hate you you are dead to me.', 'prob': 0.6264143199088837}]
Demo output: "deep-segment_punct": [
"Why you did this to me? I hate you, You are dead to me."
]

Where could the problem be? How can I get the same result as it in DeepPunct

If you need more details to locate the error, please tell me.

Thanks

Node version?

Hello,
This is great! Any chance there could be a node version?

Happy to help writing python into node js if there are no obvious limitations or blockers, and with some guidance on what to look out for.

How can I resolve this error?

Hi,

Thanks for this package. I just tried running it with the following code:

corrector = DeepCorrect('./deeppunct_params_en', './deeppunct_checkpoint_wikipedia')

However I get this error:

`

corrector = DeepCorrect('./deeppunct_params_en', './deeppunct_checkpoint_wikipedia')
Loading the params file
Input encoding {'o': 2, '{': 3, '.': 4, 'J': 5, '0': 6, '1': 7, '<': 8, 'B': 9, 'd': 10, '£': 11, 'e': 12, '6': 13, '!': 14, 'O': 15, 'M': 16, 'X': 17, 'f': 18, 't': 19, 'C': 20, 'V': 21, 'z': 22, 'K': 23, '\': 24, '9': 25, 'P': 26, 'S': 27, '/': 28, '₹': 29, 'F': 30, 'G': 31, '=': 32, '8': 33, ')': 34, '+': 35, ']': 36, 'U': 37, "'": 38, '"': 39, 'g': 40, 'N': 41, 'r': 42, 'u': 43, '&': 44, '$': 45, 'x': 46, '%': 47, ':': 48, '@': 49, '^': 50, 'I': 51, 'L': 52, 'Z': 53, 'h': 54, 'W': 55, 'A': 56, 'v': 57, '?': 58, '2': 59, '': 60, 's': 61, 'T': 62, 'R': 63, ',': 64, '|': 65, '4': 66, '>': 67, 'y': 68, '(': 69, '[': 70, 'k': 71, 'H': 72, 'l': 73, 'j': 74, '7': 75, 'n': 76, 'i': 77, 'D': 78, 'Q': 79, ' ': 80, 'm': 81, 'Y': 82, '*': 83, '}': 84, '#': 85, 'p': 86, 'q': 87, '5': 88, 'c': 89, '': 90, 'a': 91, 'b': 92, 'w': 93, '3': 94, 'E': 95, ';': 96, '-': 97} Input decoding {2: 'o', 3: '{', 4: '.', 5: 'J', 6: '0', 7: '1', 8: '<', 9: 'B', 10: 'd', 11: '£', 12: 'e', 13: '6', 14: '!', 15: 'O', 16: 'M', 17: 'X', 18: 'f', 19: 't', 20: 'C', 21: 'V', 22: 'z', 23: 'K', 24: '\\', 25: '9', 26: 'P', 27: 'S', 28: '/', 29: '₹', 30: 'F', 31: 'G', 32: '=', 33: '8', 34: ')', 35: '+', 36: ']', 37: 'U', 38: "'", 39: '"', 40: 'g', 41: 'N', 42: 'r', 43: 'u', 44: '&', 45: '$', 46: 'x', 47: '%', 48: ':', 49: '@', 50: '^', 51: 'I', 52: 'L', 53: 'Z', 54: 'h', 55: 'W', 56: 'A', 57: 'v', 58: '?', 59: '2', 60: '~', 61: 's', 62: 'T', 63: 'R', 64: ',', 65: '|', 66: '4', 67: '>', 68: 'y', 69: '(', 70: '[', 71: 'k', 72: 'H', 73: 'l', 74: 'j', 75: '7', 76: 'n', 77: 'i', 78: 'D', 79: 'Q', 80: ' ', 81: 'm', 82: 'Y', 83: '*', 84: '}', 85: '#', 86: 'p', 87: 'q', 88: '5', 89: 'c', 90: '', 91: 'a', 92: 'b', 93: 'w', 94: '3', 95: 'E', 96: ';', 97: '-'}
Output encoding {'o': 2, '{': 3, '.': 4, 'J': 5, '0': 6, '1': 7, '<': 8, 'B': 9, 'd': 10, '£': 11, 'e': 12, '6': 13, '!': 14, 'O': 15, 'M': 16, 'X': 17, 'f': 18, 't': 19, 'C': 20, 'V': 21, 'z': 22, 'K': 23, '\': 24, '9': 25, 'P': 26, 'S': 27, '/': 28, '₹': 29, 'F': 30, 'G': 31, '=': 32, '8': 33, ')': 34, '+': 35, ']': 36, 'U': 37, "'": 38, '"': 39, 'g': 40, 'N': 41, 'r': 42, 'u': 43, '&': 44, '$': 45, 'x': 46, '%': 47, ':': 48, '@': 49, '^': 50, 'I': 51, 'L': 52, 'Z': 53, 'h': 54, 'W': 55, 'A': 56, 'v': 57, '?': 58, '2': 59, '
': 60, 's': 61, 'T': 62, 'R': 63, ',': 64, '|': 65, '4': 66, '>': 67, 'y': 68, '(': 69, '[': 70, 'k': 71, 'H': 72, 'l': 73, 'j': 74, '7': 75, 'n': 76, 'i': 77, 'D': 78, 'Q': 79, ' ': 80, 'm': 81, 'Y': 82, '*': 83, '}': 84, '#': 85, 'p': 86, 'q': 87, '5': 88, 'c': 89, '': 90, 'a': 91, 'b': 92, 'w': 93, '3': 94, 'E': 95, ';': 96, '-': 97} Output decoding {2: 'o', 3: '{', 4: '.', 5: 'J', 6: '0', 7: '1', 8: '<', 9: 'B', 10: 'd', 11: '£', 12: 'e', 13: '6', 14: '!', 15: 'O', 16: 'M', 17: 'X', 18: 'f', 19: 't', 20: 'C', 21: 'V', 22: 'z', 23: 'K', 24: '\\', 25: '9', 26: 'P', 27: 'S', 28: '/', 29: '₹', 30: 'F', 31: 'G', 32: '=', 33: '8', 34: ')', 35: '+', 36: ']', 37: 'U', 38: "'", 39: '"', 40: 'g', 41: 'N', 42: 'r', 43: 'u', 44: '&', 45: '$', 46: 'x', 47: '%', 48: ':', 49: '@', 50: '^', 51: 'I', 52: 'L', 53: 'Z', 54: 'h', 55: 'W', 56: 'A', 57: 'v', 58: '?', 59: '2', 60: '~', 61: 's', 62: 'T', 63: 'R', 64: ',', 65: '|', 66: '4', 67: '>', 68: 'y', 69: '(', 70: '[', 71: 'k', 72: 'H', 73: 'l', 74: 'j', 75: '7', 76: 'n', 77: 'i', 78: 'D', 79: 'Q', 80: ' ', 81: 'm', 82: 'Y', 83: '*', 84: '}', 85: '#', 86: 'p', 87: 'q', 88: '5', 89: 'c', 90: '', 91: 'a', 92: 'b', 93: 'w', 94: '3', 95: 'E', 96: ';', 97: '-'}
Traceback (most recent call last):
File "", line 1, in
File "/Users/abhishek.shivkumar/.local/share/virtualenvs/deepsegment-87kORHDC/lib/python3.7/site-packages/deepcorrect-1.0.5-py3.7.egg/deepcorrect/deepcorrect.py", line 9, in init
File "/Users/abhishek.shivkumar/.local/share/virtualenvs/deepsegment-87kORHDC/lib/python3.7/site-packages/Keras-2.3.1-py3.7.egg/keras/engine/saving.py", line 492, in load_wrapper
return load_function(*args, **kwargs)
File "/Users/abhishek.shivkumar/.local/share/virtualenvs/deepsegment-87kORHDC/lib/python3.7/site-packages/Keras-2.3.1-py3.7.egg/keras/engine/network.py", line 1230, in load_weights
f, self.layers, reshape=reshape)
File "/Users/abhishek.shivkumar/.local/share/virtualenvs/deepsegment-87kORHDC/lib/python3.7/site-packages/Keras-2.3.1-py3.7.egg/keras/engine/saving.py", line 1235, in load_weights_from_hdf5_group
' elements.')
ValueError: Layer #1 (named "bidirectional_6" in the current model) was found to correspond to layer embedding_1 in the save file. However the new layer bidirectional_6 expects 6 weights, but the saved weights have 1 elements.

`

Can you please help me solve this?

Problem with checkpoint_path

Hi,

I am getting the following error: 'OSError: Unable to open file (unable to open file: name = 'checkpoint_path', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)'

Do you know how to fix it?

Kind regards!

How to run deepcorrect for unpunctuated text

Could you please tell me the steps needed to run deepcorrect, after cloning you repo.

  • I would like to use the pre-trained model of your demo. Where is that stored and where do I need to load it? I will like to test is on unpunctuated text.

  • What limits the sentence length in/out to 200 ? is it because of the decoder? How can I change that to be let's say 500?

Thank you!

Help with train data

input_data (list): List of input strings.
output_data (list): List of output strings.

In your model you use data like :
list of tokens - example ['Hi,'how','are','you?','Great',,'thanks!']
or
list of sentences - example ['Hi, how are you?','Great, thanks!']

AND

What are the maximum lengths you used?
max_lenghts=(?, ?)

Thanks in advance for answering a stupid question!

Pretrained model not working

Hi, I am interested in using your tool.

I have installed it via pip3, and tried your sample code:

from deepcorrect import DeepCorrect
corrector = DeepCorrect('params_path', 'checkpoint_path')
corrector.correct('hey')
'Hey!'

The problem is that

corrector = DeepCorrect('params_path', 'checkpoint_path')

returns the following message with any of the 3 pre-trained checkpoints:

Loading the params file
Input encoding {'o': 2, '{': 3, '.': 4, 'J': 5, '0': 6, '1': 7, '<': 8, 'B': 9, 'd': 10, '£': 11, 'e': 12, '6': 13, '!': 14, 'O': 15, 'M': 16, 'X': 17, 'f': 18, 't': 19, 'C': 20, 'V': 21, 'z': 22, 'K': 23, '\': 24, '9': 25, 'P': 26, 'S': 27, '/': 28, '₹': 29, 'F': 30, 'G': 31, '=': 32, '8': 33, ')': 34, '+': 35, ']': 36, 'U': 37, "'": 38, '"': 39, 'g': 40, 'N': 41, 'r': 42, 'u': 43, '&': 44, '$': 45, 'x': 46, '%': 47, ':': 48, '@': 49, '^': 50, 'I': 51, 'L': 52, 'Z': 53, 'h': 54, 'W': 55, 'A': 56, 'v': 57, '?': 58, '2': 59, '': 60, 's': 61, 'T': 62, 'R': 63, ',': 64, '|': 65, '4': 66, '>': 67, 'y': 68, '(': 69, '[': 70, 'k': 71, 'H': 72, 'l': 73, 'j': 74, '7': 75, 'n': 76, 'i': 77, 'D': 78, 'Q': 79, ' ': 80, 'm': 81, 'Y': 82, '*': 83, '}': 84, '#': 85, 'p': 86, 'q': 87, '5': 88, 'c': 89, '': 90, 'a': 91, 'b': 92, 'w': 93, '3': 94, 'E': 95, ';': 96, '-': 97} Input decoding {2: 'o', 3: '{', 4: '.', 5: 'J', 6: '0', 7: '1', 8: '<', 9: 'B', 10: 'd', 11: '£', 12: 'e', 13: '6', 14: '!', 15: 'O', 16: 'M', 17: 'X', 18: 'f', 19: 't', 20: 'C', 21: 'V', 22: 'z', 23: 'K', 24: '\\', 25: '9', 26: 'P', 27: 'S', 28: '/', 29: '₹', 30: 'F', 31: 'G', 32: '=', 33: '8', 34: ')', 35: '+', 36: ']', 37: 'U', 38: "'", 39: '"', 40: 'g', 41: 'N', 42: 'r', 43: 'u', 44: '&', 45: '$', 46: 'x', 47: '%', 48: ':', 49: '@', 50: '^', 51: 'I', 52: 'L', 53: 'Z', 54: 'h', 55: 'W', 56: 'A', 57: 'v', 58: '?', 59: '2', 60: '~', 61: 's', 62: 'T', 63: 'R', 64: ',', 65: '|', 66: '4', 67: '>', 68: 'y', 69: '(', 70: '[', 71: 'k', 72: 'H', 73: 'l', 74: 'j', 75: '7', 76: 'n', 77: 'i', 78: 'D', 79: 'Q', 80: ' ', 81: 'm', 82: 'Y', 83: '*', 84: '}', 85: '#', 86: 'p', 87: 'q', 88: '5', 89: 'c', 90: '', 91: 'a', 92: 'b', 93: 'w', 94: '3', 95: 'E', 96: ';', 97: '-'}
Output encoding {'o': 2, '{': 3, '.': 4, 'J': 5, '0': 6, '1': 7, '<': 8, 'B': 9, 'd': 10, '£': 11, 'e': 12, '6': 13, '!': 14, 'O': 15, 'M': 16, 'X': 17, 'f': 18, 't': 19, 'C': 20, 'V': 21, 'z': 22, 'K': 23, '\': 24, '9': 25, 'P': 26, 'S': 27, '/': 28, '₹': 29, 'F': 30, 'G': 31, '=': 32, '8': 33, ')': 34, '+': 35, ']': 36, 'U': 37, "'": 38, '"': 39, 'g': 40, 'N': 41, 'r': 42, 'u': 43, '&': 44, '$': 45, 'x': 46, '%': 47, ':': 48, '@': 49, '^': 50, 'I': 51, 'L': 52, 'Z': 53, 'h': 54, 'W': 55, 'A': 56, 'v': 57, '?': 58, '2': 59, '
': 60, 's': 61, 'T': 62, 'R': 63, ',': 64, '|': 65, '4': 66, '>': 67, 'y': 68, '(': 69, '[': 70, 'k': 71, 'H': 72, 'l': 73, 'j': 74, '7': 75, 'n': 76, 'i': 77, 'D': 78, 'Q': 79, ' ': 80, 'm': 81, 'Y': 82, '*': 83, '}': 84, '#': 85, 'p': 86, 'q': 87, '5': 88, 'c': 89, '': 90, 'a': 91, 'b': 92, 'w': 93, '3': 94, 'E': 95, ';': 96, '-': 97} Output decoding {2: 'o', 3: '{', 4: '.', 5: 'J', 6: '0', 7: '1', 8: '<', 9: 'B', 10: 'd', 11: '£', 12: 'e', 13: '6', 14: '!', 15: 'O', 16: 'M', 17: 'X', 18: 'f', 19: 't', 20: 'C', 21: 'V', 22: 'z', 23: 'K', 24: '\\', 25: '9', 26: 'P', 27: 'S', 28: '/', 29: '₹', 30: 'F', 31: 'G', 32: '=', 33: '8', 34: ')', 35: '+', 36: ']', 37: 'U', 38: "'", 39: '"', 40: 'g', 41: 'N', 42: 'r', 43: 'u', 44: '&', 45: '$', 46: 'x', 47: '%', 48: ':', 49: '@', 50: '^', 51: 'I', 52: 'L', 53: 'Z', 54: 'h', 55: 'W', 56: 'A', 57: 'v', 58: '?', 59: '2', 60: '~', 61: 's', 62: 'T', 63: 'R', 64: ',', 65: '|', 66: '4', 67: '>', 68: 'y', 69: '(', 70: '[', 71: 'k', 72: 'H', 73: 'l', 74: 'j', 75: '7', 76: 'n', 77: 'i', 78: 'D', 79: 'Q', 80: ' ', 81: 'm', 82: 'Y', 83: '*', 84: '}', 85: '#', 86: 'p', 87: 'q', 88: '5', 89: 'c', 90: '', 91: 'a', 92: 'b', 93: 'w', 94: '3', 95: 'E', 96: ';', 97: '-'}
Traceback (most recent call last):
File "", line 1, in
File "/home/toliz/.local/lib/python3.6/site-packages/deepcorrect/deepcorrect.py", line 8, in init
DeepCorrect.deepcorrect_model = build_model(params_path)
File "/home/toliz/.local/lib/python3.6/site-packages/txt2txt/txt2txt.py", line 204, in build_model
decoder = LSTM(2 * enc_lstm_units, return_sequences=True, unroll=unroll)(decoder, initial_state=[encoder_last, encoder_last])
File "/home/toliz/.local/lib/python3.6/site-packages/keras/layers/recurrent.py", line 574, in call
return super(RNN, self).call(inputs, **kwargs)
File "/home/toliz/.local/lib/python3.6/site-packages/keras/engine/base_layer.py", line 431, in call
self.build(unpack_singleton(input_shapes))
File "/home/toliz/.local/lib/python3.6/site-packages/keras/layers/recurrent.py", line 503, in build
if [spec.shape[-1] for spec in self.state_spec] != state_size:
File "/home/toliz/.local/lib/python3.6/site-packages/keras/layers/recurrent.py", line 503, in
if [spec.shape[-1] for spec in self.state_spec] != state_size:
TypeError: 'NoneType' object is not subscriptable

Could you please help me? I am using Ubuntu 18.04 and python 3.6

sentence is not punctuated properly

when i

from deepcorrect import DeepCorrect

corrector = DeepCorrect(deeppunct_params_en, deeppunct_checkpoint_tatoeba_cornell)

corrector.correct('hey')

it is giving me "hey."

and when i

corrector.correct('hello how are you what is your name')

it gives me 'Hello, how are you what is your name.'

no question marks , why?.

please help me what should i do?

output the text only

from deepcorrect import DeepCorrect

checkpoint_path = "./deep_punct_v2_model/deeppunct_checkpoint_wikipedia"
params_path = "./deep_punct_v2_model/deeppunct_params_en"

corrector = DeepCorrect(params_path, checkpoint_path)
corrector.correct('how are you')

This is my output:
[{'sequence': 'How are you?', 'prob': 0.9735229413488089}]

I only want to print the 'How are you?' without printing the sequence and prob. What should I do?

How train model

Hi. I want add ukraine language to it. I cannot found tutorial for train model manually

Incorrect Results

Hi, I tried training txt2txt on a German dataset for punctuation correction. Then used deepcorrect to punctuate the text, but the results are incorrect. Could you please guide on this?

I passed the training data itself. But output is consistently 3 words. Please guide.

corrector.correct("in keiner dieser debatten wurden diese grundsätze irgendwie bestritten oder angezweifelt")
[[{'sequence': 'in keiner', 'prob': 0.26473349747315716}]]
corrector.correct("es geht mir in diesem kontext darum spielraum zu schaffen für zwei dinge")
[[{'sequence': 'es geht m', 'prob': 0.1473360733543895}]]

Unable to import and use the package

from deepcorrect import DeepCorrect corrector = DeepCorrect('params_path', 'checkpoint_path') corrector.correct('how are you')

im getting error like
`Traceback (most recent call last):

File "C:\Users\skullcandy\AppData\Roaming\Python\Python38\site-packages\IPython\core\interactiveshell.py", line 3331, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)

File "", line 1, in
from deepcorrect import DeepCorrect

File "C:\Users\skullcandy\AppData\Local\Programs\Python\Python38-32\lib\site-packages\deepcorrect_init_.py", line 1, in
from .deepcorrect import DeepCorrect

File "C:\Users\skullcandy\AppData\Local\Programs\Python\Python38-32\lib\site-packages\deepcorrect\deepcorrect.py", line 1, in
from txt2txt import build_model, infer

File "C:\Users\skullcandy\AppData\Local\Programs\Python\Python38-32\lib\site-packages\txt2txt_init_.py", line 3, in
from .txt2txt import *

File "C:\Users\skullcandy\AppData\Local\Programs\Python\Python38-32\lib\site-packages\txt2txt\txt2txt.py", line 7, in
import tensorflow as tf

File "C:\Users\skullcandy\AppData\Local\Programs\Python\Python38-32\lib\site-packages\tensorflow_init_.py", line 24, in
from tensorflow.python import pywrap_tensorflow # pylint: disable=unused-import

File "C:\Users\skullcandy\AppData\Local\Programs\Python\Python38-32\lib\site-packages\tensorflow\python_init_.py", line 49, in
from tensorflow.python import pywrap_tensorflow

File "C:\Users\skullcandy\AppData\Local\Programs\Python\Python38-32\lib\site-packages\tensorflow\python\pywrap_tensorflow.py", line 58, in
from tensorflow.python.pywrap_tensorflow_internal import *

File "C:\Users\skullcandy\AppData\Local\Programs\Python\Python38-32\lib\site-packages\tensorflow\python\pywrap_tensorflow_internal.py", line 114
def TFE_ContextOptionsSetAsync(arg1, async):
^
SyntaxError: invalid syntax
`

Can you help me in using it

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.