-
I'm trying to train FastText for performing Information Extraction (which is considered as a text classification problem) on a big corpus where the positive examples (speakers) are not organized one p…
-
New release of `gensim==3.7.2` broke several things in `CandidateGenerator` in `typos`:
1. Loading fasttext model from the file - _easy fix_.
2. Modelforge save/load functions are now broken becau…
-
Test DPK on windows machine using the latest dpk library from pypi
Update the documentation (readme) on how a user can run dpk on windows
-
I am very interested in your fastText model for filtering data, and I wonder if you can provide relevant weights for this model for learning and research?
-
I was surprised to learn that the `langid` filter is CLD2 and the `fasttext_filter` is fasttext langid. From a UI perspective, its better to have one.
Aside, can we add Laurie's LID?
-
- [x] bak-tat
- [x] kir-kaz
- [x] crh-tat
- [x] crh-kaz
- [x] crh-tur
- [x] kaz-tat
- [x] kaz-tur
- [x] tat-tur
to put file into mega: `mega-put ast/ast.txt -c mycooldir/`
to get file from …
-
## Tasks
- [x] NLP model research:
- fasttext
- [ ] Decision - TensorFlow lite?
- [x] ML in browser
## Research
- [ ] whether web_speech API is supported on phones?
- [ ] Start mobile test…
-
### Description of the bug | 错误描述
采用版本为0.7.0b1，在运行测试时出现ValueError: Unable to avoid copy while creating an array as requested.报错，完整内容如下：
2024-08-13 16:23:06.329 | ERROR | magic_pdf.tools.cli:parse…
-
See https://github.com/facebookresearch/fastText
Fast and accurate text classification.
-
Could you please provide a working example for loading the fasttext binary, including support for OOV words? thanks