segment-any-text wtpsplit issues

segment-any-text / wtpsplit

Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.

MIT License

752 stars 44 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

No lookahead models

#143 arinaruck opened 1 hour ago
0
AssertionError on empty input text

#142 lifeiteng opened 4 hours ago
0
2.1.1 treats \n as empty string

#141 alexander-0000 opened 1 week ago
0
AttributeError: 'SubwordXLMForTokenClassification' object has no attribute 'split'

#140 benx13 closed 3 weeks ago
2
ImportError: cannot import name 'SaT' from 'wtpsplit' (/usr/local/lib/python3.10/site-packages/wtpsplit/__init__.py)

#139 hwang136 closed 2 weeks ago
4
Which setting is the best for scientific sentence segmentation with inline citations and potential parsing error

#138 realliyifei opened 1 month ago
1
KeyError: 'xlm-token'

#137 amurtadha closed 1 month ago
1
Fix/huggingface hub

#136 carschno closed 4 weeks ago
0
ImportError with language and style_or_domain arguments and huggingface-hub 0.26

#135 carschno closed 4 weeks ago
2
no-limited-lookahead models

#134 Qubitium closed 1 month ago
1
Korean text is not split well

#133 seungduk-yanolja closed 4 weeks ago
4
Update README for LoRA

#132 markus583 closed 4 weeks ago
0
Newlines are treated like spaces

#131 markus583 closed 4 weeks ago
5
Questions concerning configuring train_lora.py for custom corpus

#130 eshau opened 2 months ago
8
add ONNX support for SaT models

#129 markus583 closed 2 months ago
2
Add option to limit the maximum length of each split text segment

#128 Swarzox opened 2 months ago
1
Single words incorrectly segmented into character sequences

#127 lhcoder closed 2 months ago
4
Relax the requirements on numpy to allow numpy 2.0+

#126 si14 closed 3 months ago
3
Set transformers dependency to >=4.40.0 for consistency with setup.py.

#125 carschno closed 3 months ago
1
Update transformers dependency

#124 carschno closed 3 months ago
3
Failed to Adapt to your own corpus via LoRA

#123 12eue closed 2 months ago
8
Error when installing the requirements

#122 RacheleSprugnoli closed 4 months ago
2
CUDA device error when segmenting Greek text

#121 ayalda closed 4 months ago
1
sat-12l-sm running on GPU

#120 Randwow closed 4 months ago
6
Run models for Italian

#119 RacheleSprugnoli closed 4 months ago
2
SaT is slow

#118 thegenerativegeneration closed 4 months ago
2
Add SaT

#117 bminixhofer closed 5 months ago
0
Update Docs

#116 bminixhofer closed 5 months ago
0
Canine model and High VRAM usage

#115 Qubitium closed 1 month ago
7
Please explain length of output of wtp.predict_proba(text)

#114 gaggiag closed 9 months ago
3
Accuracy: Error in Split (EN)

#113 Qubitium closed 10 months ago
1
Huggingface AutoModelForTokenClassification bug

#112 asusdisciple closed 9 months ago
4
remove_repetition

#111 mmichelli closed 11 months ago
2
model in huggingface cannot load mixtures.skops

#110 syeelou closed 1 year ago
1
Rust bindings for wtpsplit

#109 turulix opened 1 year ago
0
How to use Universal Dependencies style ?

#108 Lix1993 closed 1 year ago
3
Could not find a mixture for the Universal Dependencies (UD) style in Thai language

#107 pavaris-pm closed 1 year ago
1
For GPU, ONNX WtP model is around 2x slower than PyTorch.

#106 Phuoc-Hoan-Le closed 1 year ago
2
InconsistentVersionWarning Issue everytime I start wtp

#105 TutubanaS closed 1 month ago
2
Scoring metric, does definition make sense?

#104 asusdisciple closed 1 year ago
1
Inconsistent results with same sentences

#103 asusdisciple closed 5 months ago
5
wtp-canine-s-1l-no-adapters - missing mixtures.skops

#102 intelliqua closed 1 month ago
1
Model(s) use word capitlisation to segment

#101 intelliqua closed 5 months ago
11
Async - Skops import is failing

#100 MathiasExorde closed 1 year ago
7
Opus100 FR not in mixtures

#99 intelliqua closed 1 year ago
1
Any string that isn't a multiple of 4 causes an assert failure

#98 intelliqua closed 1 year ago
2
fix getattr

#97 bminixhofer closed 1 year ago
0
Recursion in init

#96 jonvaughan closed 12 months ago
2
Error loading model to GPU

#95 damin604 closed 1 year ago
1
Faster preprocessing, Full ONNXRuntime support for BERT-style models, CI

#94 bminixhofer closed 1 year ago
0