Re-uploading model

README.md

@@ -1,3 +1,63 @@
 ---
-license: apache-2.0
+license: mit
 ---
+# Bengali to English Word Aligner
+Finetuned Model for **Bengali to English Word** which was build on `bert-base-multilingual-cased`
+
+## Quick Start
+Initialize to use it in your project
+
+```python
+tokenizer = AutoTokenizer.from_pretrained("musfiqdehan/bengali-english-word-aligner")
+model = AutoModel.from_pretrained("musfiqdehan/bengali-english-word-aligner")
+```
+## Bengali-English Word Alignment
+
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1x5wUXS7vdWNeROkJS_B_lUwKTJZGaB7v?usp=sharing)
+
+[![Kaggle](https://kaggle.com/static/images/open-in-kaggle.svg)](https://www.kaggle.com/musfiqdehan/bengali-english-alignment-demo)
+
+Install Dependencies
+```
+!pip install -U data-preprocessors
+!pip install -U bangla-postagger
+```
+Import Necessary Libraries
+```python
+from pprint import pprint
+from data_preprocessors import text_preprocessor as tp
+from bangla_postagger import (en_postaggers as ep,
+                              bn_en_mapper as bem,
+                              translators as trans)
+```
+
+Testing Word Mapping and Alignment
+
+```python
+src = "আমি ভাত খাই না, রুটি খাই।"
+tgt = "I do not eat rice, I eat bread."
+
+# Give one space before and after punctuation
+# for easy tokenization
+src = tp.space_punc(src)
+tgt = tp.space_punc(tgt)
+
+print("Word Mapping:")
+mapping = bem.get_word_mapping(
+    source=src, target=tgt, model_path="musfiqdehan/bengali-english-word-aligner")
+pprint(mapping)
+```
+
+Output
+```
+Word Mapping:
+['bn:(আমি) -> en:(I)',
+ 'bn:(ভাত) -> en:(rice)',
+ 'bn:(খাই) -> en:(do)',
+ 'bn:(খাই) -> en:(eat)',
+ 'bn:(না) -> en:(not)',
+ 'bn:(,) -> en:(,)',
+ 'bn:(রুটি) -> en:(bread)',
+ 'bn:(খাই) -> en:(eat)',
+ 'bn:(।) -> en:(.)']
+```

config.json

@@ -0,0 +1,52 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "directionality": "bidi",
+  "do_sample": false,
+  "eos_token_ids": null,
+  "finetuning_task": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_beams": 1,
+  "num_hidden_layers": 12,
+  "num_labels": 2,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "repetition_penalty": 1.0,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "torchscript": false,
+  "type_vocab_size": 2,
+  "use_bfloat16": false,
+  "vocab_size": 119547
+}

eval_results.txt

@@ -0,0 +1 @@
+perplexity = tensor(2.0303)

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68156f53b7bd3ce8c9d13dac14f0762adc9029c0576b842c796f60f22f23755
+size 1081597091

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "max_len": 512}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26d53ebc8dc10dcb2c2bc2ec410499a5977ef4b409dae466e5fb183b25592de
+size 1711