Update README.md

README.md

@@ -42,10 +42,10 @@ def strip_accents_and_lowercase(s):
    return ''.join(c for c in unicodedata.normalize('NFD', s)
                   if unicodedata.category(c) != 'Mn').lower()
 
-accented_string = "Αυτή είναι η Ελληνική έκδοση του BERT."
+accented_string = "Τούτη εν η Κυπριακή έκδοση του BERT."
 unaccented_string = strip_accents_and_lowercase(accented_string)
 
-print(unaccented_string) # αυτη ειναι η ελληνικη εκδοση του bert.
+print(unaccented_string) # τουτη εν η κυπριακη εκδοση του bert.
 
 ```
 
@@ -71,35 +71,21 @@ tokenizer_cypriot = AutoTokenizer.from_pretrained('petros/bert-base-cypriot-unca
 lm_model_cypriot = AutoModelWithLMHead.from_pretrained('petros/bert-base-cypriot-uncased-v1')
 
 # ================ EXAMPLE 1 ================
-text_1 = 'Θώρει τη [MASK].'
-# EN: 'Sees the [MASK].'
+text_1 = 'Τι [MASK] ρε'
 input_ids = tokenizer_cypriot.encode(text_1)
-print(tokenizer_cypriot.convert_ids_to_tokens(input_ids))
-# ['[CLS]', 'o', 'ποιητης', 'εγραψε', 'ενα', '[MASK]', '.', '[SEP]']
+print(tokenizer_cypriot.convert_ids_to_tokens(input_ids)) # ['[CLS]', 'τι', '[MASK]', 'ρε', '[SEP]']
+
 outputs = lm_model_cypriot(torch.tensor([input_ids]))[0]
-print(tokenizer_greek.convert_ids_to_tokens(outputs[0, 5].max(0)[1].item()))
-# the most plausible prediction for [MASK] is "song"
+print(tokenizer_cypriot.convert_ids_to_tokens(outputs[0, 2].max(0)[1].item())) # ειδους
 
 # ================ EXAMPLE 2 ================
-text_2 = 'Είναι ένας [MASK] άνθρωπος.'
-# EN: 'He is a [MASK] person.'
+text_2 = 'Eίσαι μια [MASK].'
 input_ids = tokenizer_greek.encode(text_2)
-print(tokenizer_greek.convert_ids_to_tokens(input_ids))
-# ['[CLS]', 'ειναι', 'ενας', '[MASK]', 'ανθρωπος', '.', '[SEP]']
-outputs = lm_model_greek(torch.tensor([input_ids]))[0]
-print(tokenizer_greek.convert_ids_to_tokens(outputs[0, 3].max(0)[1].item()))
-# the most plausible prediction for [MASK] is "good"
-
-# ================ EXAMPLE 3 ================
-text_3 = 'Είναι ένας [MASK] άνθρωπος και κάνει συχνά [MASK].'
-# EN: 'He is a [MASK] person he does frequently [MASK].'
-input_ids = tokenizer_greek.encode(text_3)
-print(tokenizer_greek.convert_ids_to_tokens(input_ids))
-# ['[CLS]', 'ειναι', 'ενας', '[MASK]', 'ανθρωπος', 'και', 'κανει', 'συχνα', '[MASK]', '.', '[SEP]']
+print(tokenizer_greek.convert_ids_to_tokens(input_ids)) #['[CLS]', 'eισ', '##αι', 'μια', '[MASK]', '.', '[SEP]']
+
 outputs = lm_model_greek(torch.tensor([input_ids]))[0]
-print(tokenizer_greek.convert_ids_to_tokens(outputs[0, 8].max(0)[1].item()))
-# the most plausible prediction for the second [MASK] is "trips"
-```
+print(tokenizer_greek.convert_ids_to_tokens(outputs[0, 3].max(0)[1].item())) # χαρα
+
 
 About Me
 Petros Andreou