Update README.md

README.md

@@ -1,3 +1,151 @@
 ---
-license: mit
+license: apache-2.0
+library_name: transformers
 ---
+# Model Description
+
+The transformer-eng-por model is used to ... More information is needed.
+
+The model was trained with a ...More information is needed.
+
+## Details
+- Size: 23,805,216 parameters
+- Dataset: 
+- Languages: English
+- Number of Training Steps: 30
+- Batch size: 32
+- Optimizer: rmsprop
+- Learning Rate: 0.001
+- GPU: T4
+- This repository has the source [code used](https://github.com/Nkluge-correa/teeny-tiny_castle/blob/master/ML%20Intro%20Course/16_sequence_to_sequence.ipynb) to train this model.
+
+## Usage
+
+```
+import tensorflow as tf
+import numpy as np
+import string
+import keras
+import re
+
+strip_chars = string.punctuation
+strip_chars = strip_chars.replace("[", "")
+strip_chars = strip_chars.replace("]", "")
+
+
+def custom_standardization(input_string):
+    lowercase = tf.strings.lower(input_string)
+    return tf.strings.regex_replace(lowercase, f"[{re.escape(strip_chars)}]", "")
+
+portuguese_vocabulary_path = hf_hub_download(
+    repo_id="AiresPucrs/transformer-eng-por",
+    filename="keras_transformer_blocks.py",
+    repo_type='model',
+    local_dir="./")
+
+from keras_transformer_blocks import TransformerEncoder, PositionalEmbedding, TransformerDecoder
+
+transformer = keras.models.load_model("/content/transformer-eng-por/transformer-eng-por.h5",
+    custom_objects={"TransformerEncoder": TransformerEncoder,
+        "PositionalEmbedding": PositionalEmbedding,
+        "TransformerDecoder": TransformerDecoder})
+
+with open('portuguese_vocabulary.txt', encoding='utf-8', errors='backslashreplace') as fp:
+    portuguese_vocab = [line.strip() for line in fp]
+    fp.close()
+
+with open('english_vocabulary.txt', encoding='utf-8', errors='backslashreplace') as fp:
+    english_vocab = [line.strip() for line in fp]
+    fp.close()
+
+
+target_vectorization = tf.keras.layers.TextVectorization(max_tokens=20000,
+                                        output_mode="int",
+                                        output_sequence_length=21,
+                                        standardize=custom_standardization,
+                                        vocabulary=portuguese_vocab)
+
+source_vectorization = tf.keras.layers.TextVectorization(max_tokens=20000,
+                                        output_mode="int",
+                                        output_sequence_length=20,
+                                        vocabulary=english_vocab)
+
+portuguese_index_lookup = dict(zip(range(len(portuguese_vocab)), portuguese_vocab))
+max_decoded_sentence_length = 20
+
+
+def decode_sequence(input_sentence):
+    tokenized_input_sentence = source_vectorization([input_sentence])
+    decoded_sentence = "[start]"
+
+    for i in range(max_decoded_sentence_length):
+        tokenized_target_sentence = target_vectorization([decoded_sentence])[:, :-1]
+        predictions = transformer([tokenized_input_sentence, tokenized_target_sentence])
+        sampled_token_index = np.argmax(predictions[0, i, :])
+        sampled_token = portuguese_index_lookup[sampled_token_index]
+        decoded_sentence += " " + sampled_token
+        if sampled_token == "[end]":
+            break
+    return decoded_sentence
+
+
+eng_sentences =["What is its name?",
+                "How old are you?",
+                "I know you know where Mary is.",
+                "We will show Tom.",
+                "What do you all do?",
+                "Don't do it!"]
+
+for sentence in eng_sentences:
+    print(f"English sentence:\n{sentence}")
+    print(f'Portuguese translation:\n{decode_sequence(sentence)}')
+    print('-' * 50)
+```
+This will output the following:
+
+```
+English sentence:
+What is its name?
+Portuguese translation:
+[start] qual é o nome dele [end]
+--------------------------------------------------
+English sentence:
+How old are you?
+Portuguese translation:
+[start] quantos anos você tem [end]
+--------------------------------------------------
+English sentence:
+I know you know where Mary is.
+Portuguese translation:
+[start] eu sei que você sabe onde mary está [end]
+--------------------------------------------------
+English sentence:
+We will show Tom.
+Portuguese translation:
+[start] vamos ligar para o tom [end]
+--------------------------------------------------
+English sentence:
+What do you all do?
+Portuguese translation:
+[start] o que vocês todos nós têm feito [end]
+--------------------------------------------------
+English sentence:
+Don't do it!
+Portuguese translation:
+[start] não faça isso [end]
+--------------------------------------------------
+```
+# Cite as 🤗
+```
+@misc{teenytinycastle,
+    doi = {10.5281/zenodo.7112065},
+    url = {https://huggingface.co/AiresPucrs/transformer-eng-por},
+    author = {Nicholas Kluge Corr{\^e}a},
+    title = {Teeny-Tiny Castle},
+    year = {2023},
+    publisher = {HuggingFace},
+    journal = {HuggingFace repository},
+}
+```
+## License
+The transformer-eng-por is licensed under the Apache License, Version 2.0. See the LICENSE file for more details.