From a622705ef3fadbca81a940a310875bf3a9b0b4d1 Mon Sep 17 00:00:00 2001 From: Sagor Sarker Date: Mon, 24 Aug 2020 15:08:32 +0600 Subject: [PATCH] added multiple model_cards for below models (#6666) * Create README.md * Update README.md * Create README.md * Update README.md * added multiple codeswitch model --- .../codeswitch-hineng-lid-lince/README.md | 1 + .../codeswitch-hineng-ner-lince/README.md | 47 +++++++++++++++++++ .../codeswitch-hineng-pos-lince/README.md | 45 ++++++++++++++++++ .../codeswitch-nepeng-lid-lince/README.md | 47 +++++++++++++++++++ .../codeswitch-spaeng-lid-lince/README.md | 1 + .../codeswitch-spaeng-ner-lince/README.md | 46 ++++++++++++++++++ .../codeswitch-spaeng-pos-lince/README.md | 45 ++++++++++++++++++ 7 files changed, 232 insertions(+) create mode 100644 model_cards/sagorsarker/codeswitch-hineng-ner-lince/README.md create mode 100644 model_cards/sagorsarker/codeswitch-hineng-pos-lince/README.md create mode 100644 model_cards/sagorsarker/codeswitch-nepeng-lid-lince/README.md create mode 100644 model_cards/sagorsarker/codeswitch-spaeng-ner-lince/README.md create mode 100644 model_cards/sagorsarker/codeswitch-spaeng-pos-lince/README.md diff --git a/model_cards/sagorsarker/codeswitch-hineng-lid-lince/README.md b/model_cards/sagorsarker/codeswitch-hineng-lid-lince/README.md index f7da9444a4..06e8651066 100644 --- a/model_cards/sagorsarker/codeswitch-hineng-lid-lince/README.md +++ b/model_cards/sagorsarker/codeswitch-hineng-lid-lince/README.md @@ -7,6 +7,7 @@ language: # codeswitch-hineng-lid-lince This is a pretrained model for **language identification** of `hindi-english` code-mixed data used from [LinCE](https://ritual.uh.edu/lince/home) + ## Identify Language * Method-1 diff --git a/model_cards/sagorsarker/codeswitch-hineng-ner-lince/README.md b/model_cards/sagorsarker/codeswitch-hineng-ner-lince/README.md new file mode 100644 index 0000000000..c16332ce55 --- /dev/null +++ b/model_cards/sagorsarker/codeswitch-hineng-ner-lince/README.md @@ -0,0 +1,47 @@ +--- +language: +- hi +- en +--- + +# codeswitch-hineng-ner-lince +This is a pretrained model for **Name Entity Recognition** of `Hindi-english` code-mixed data used from [LinCE](https://ritual.uh.edu/lince/home) + +This model is trained for this below repository. + +[https://github.com/sagorbrur/codeswitch](https://github.com/sagorbrur/codeswitch) + +To install codeswitch: + +``` +pip install codeswitch +``` + +## Identify Language + +* Method-1 + +```py + +from transformers import AutoTokenizer, AutoModelForTokenClassification + +tokenizer = AutoTokenizer.from_pretrained("sagorsarker/codeswitch-hineng-ner-lince") + +model = AutoModelForTokenClassification.from_pretrained("sagorsarker/codeswitch-hineng-ner-lince") + +ner_model = pipeline('ner', model=model, tokenizer=tokenizer) + +ner_model("put any hindi english code-mixed sentence") + +``` + +* Method-2 + +```py +from codeswitch.codeswitch import NER +ner = NER('hin-eng') +text = "" # your mixed sentence +result = ner.tag(text) +print(result) + +``` diff --git a/model_cards/sagorsarker/codeswitch-hineng-pos-lince/README.md b/model_cards/sagorsarker/codeswitch-hineng-pos-lince/README.md new file mode 100644 index 0000000000..9b253fb774 --- /dev/null +++ b/model_cards/sagorsarker/codeswitch-hineng-pos-lince/README.md @@ -0,0 +1,45 @@ +--- +language: +- hi +- en +--- + +# codeswitch-hineng-pos-lince +This is a pretrained model for **Part of Speech Tagging** of `hindi-english` code-mixed data used from [LinCE](https://ritual.uh.edu/lince/home) + +This model is trained for this below repository. + +[https://github.com/sagorbrur/codeswitch](https://github.com/sagorbrur/codeswitch) + +To install codeswitch: + +``` +pip install codeswitch +``` + +## Identify Language + +* Method-1 + +```py + +from transformers import AutoTokenizer, AutoModelForTokenClassification + +tokenizer = AutoTokenizer.from_pretrained("sagorsarker/codeswitch-hineng-pos-lince") + +model = AutoModelForTokenClassification.from_pretrained("sagorsarker/codeswitch-hineng-pos-lince") +pos_model = pipeline('ner', model=model, tokenizer=tokenizer) + +pos_model("put any hindi english code-mixed sentence") + +``` + +* Method-2 + +```py +from codeswitch.codeswitch import POS +pos = POS('hin-eng') +text = "" # your mixed sentence +result = pos.tag(text) +print(result) +``` diff --git a/model_cards/sagorsarker/codeswitch-nepeng-lid-lince/README.md b/model_cards/sagorsarker/codeswitch-nepeng-lid-lince/README.md new file mode 100644 index 0000000000..74991cd4da --- /dev/null +++ b/model_cards/sagorsarker/codeswitch-nepeng-lid-lince/README.md @@ -0,0 +1,47 @@ +--- +language: +- ne +- en +--- + +# codeswitch-nepeng-lid-lince +This is a pretrained model for **language identification** of `nepali-english` code-mixed data used from [LinCE](https://ritual.uh.edu/lince/home). + +This model is trained for this below repository. + +[https://github.com/sagorbrur/codeswitch](https://github.com/sagorbrur/codeswitch) + +To install codeswitch: + +``` +pip install codeswitch +``` + +## Identify Language + +* Method-1 + +```py + +from transformers import AutoTokenizer, AutoModelForTokenClassification + +tokenizer = AutoTokenizer.from_pretrained("sagorsarker/codeswitch-nepeng-lid-lince") + +model = AutoModelForTokenClassification.from_pretrained("sagorsarker/codeswitch-nepeng-lid-lince") +lid_model = pipeline('ner', model=model, tokenizer=tokenizer) + +lid_model("put any nepali english code-mixed sentence") + +``` + +* Method-2 + +```py +from codeswitch.codeswitch import LanguageIdentification +lid = LanguageIdentification('nep-eng') +text = "" # your code-mixed sentence +result = lid.identify(text) +print(result) + +``` + diff --git a/model_cards/sagorsarker/codeswitch-spaeng-lid-lince/README.md b/model_cards/sagorsarker/codeswitch-spaeng-lid-lince/README.md index 451364bf29..253a9eeb51 100644 --- a/model_cards/sagorsarker/codeswitch-spaeng-lid-lince/README.md +++ b/model_cards/sagorsarker/codeswitch-spaeng-lid-lince/README.md @@ -7,6 +7,7 @@ language: # codeswitch-spaeng-lid-lince This is a pretrained model for **language identification** of `spanish-english` code-mixed data used from [LinCE](https://ritual.uh.edu/lince/home) + ## Identify Language * Method-1 diff --git a/model_cards/sagorsarker/codeswitch-spaeng-ner-lince/README.md b/model_cards/sagorsarker/codeswitch-spaeng-ner-lince/README.md new file mode 100644 index 0000000000..0b2bf3d9a3 --- /dev/null +++ b/model_cards/sagorsarker/codeswitch-spaeng-ner-lince/README.md @@ -0,0 +1,46 @@ +--- +language: +- es +- en +--- + +# codeswitch-spaeng-ner-lince +This is a pretrained model for **Name Entity Recognition** of `spanish-english` code-mixed data used from [LinCE](https://ritual.uh.edu/lince/home) + +This model is trained for this below repository. + +[https://github.com/sagorbrur/codeswitch](https://github.com/sagorbrur/codeswitch) + +To install codeswitch: + +``` +pip install codeswitch +``` + +## Identify Language + +* Method-1 + +```py + +from transformers import AutoTokenizer, AutoModelForTokenClassification + +tokenizer = AutoTokenizer.from_pretrained("sagorsarker/codeswitch-spaeng-ner-lince") + +model = AutoModelForTokenClassification.from_pretrained("sagorsarker/codeswitch-spaeng-ner-lince") + +ner_model = pipeline('ner', model=model, tokenizer=tokenizer) + +ner_model("put any spanish english code-mixed sentence") + +``` + +* Method-2 + +```py +from codeswitch.codeswitch import NER +ner = NER('spa-eng') +text = "" # your mixed sentence +result = ner.tag(text) +print(result) +``` diff --git a/model_cards/sagorsarker/codeswitch-spaeng-pos-lince/README.md b/model_cards/sagorsarker/codeswitch-spaeng-pos-lince/README.md new file mode 100644 index 0000000000..5710c79da4 --- /dev/null +++ b/model_cards/sagorsarker/codeswitch-spaeng-pos-lince/README.md @@ -0,0 +1,45 @@ +--- +language: +- es +- en +--- + +# codeswitch-spaeng-pos-lince +This is a pretrained model for **Part of Speech Tagging** of `spanish-english` code-mixed data used from [LinCE](https://ritual.uh.edu/lince/home) + +This model is trained for this below repository. + +[https://github.com/sagorbrur/codeswitch](https://github.com/sagorbrur/codeswitch) + +To install codeswitch: + +``` +pip install codeswitch +``` + +## Identify Language + +* Method-1 + +```py + +from transformers import AutoTokenizer, AutoModelForTokenClassification + +tokenizer = AutoTokenizer.from_pretrained("sagorsarker/codeswitch-spaeng-pos-lince") + +model = AutoModelForTokenClassification.from_pretrained("sagorsarker/codeswitch-spaeng-pos-lince") +pos_model = pipeline('ner', model=model, tokenizer=tokenizer) + +pos_model("put any spanish english code-mixed sentence") + +``` + +* Method-2 + +```py +from codeswitch.codeswitch import POS +pos = POS('spa-eng') +text = "" # your mixed sentence +result = pos.tag(text) +print(result) +```