Update README.md

README.md

@@ -39,34 +39,26 @@ tokenizer = AutoTokenizer.from_pretrained("ai4bharat/MultiIndicParaphraseGenerat
 # Or use tokenizer = AlbertTokenizer.from_pretrained("ai4bharat/MultiIndicParaphraseGeneration", do_lower_case=False, use_fast=False, keep_accents=True)
 model = AutoModelForSeq2SeqLM.from_pretrained("ai4bharat/MultiIndicParaphraseGeneration")
 # Or use model = MBartForConditionalGeneration.from_pretrained("ai4bharat/MultiIndicParaphraseGeneration")
+
 # Some initial mapping
 bos_id = tokenizer._convert_token_to_id_with_added_voc("<s>")
 eos_id = tokenizer._convert_token_to_id_with_added_voc("</s>")
 pad_id = tokenizer._convert_token_to_id_with_added_voc("<pad>")
+
 # To get lang_id use any of ['<2as>', '<2bn>', '<2en>', '<2gu>', '<2hi>', '<2kn>', '<2ml>', '<2mr>', '<2or>', '<2pa>', '<2ta>', '<2te>']
-# First tokenize the input and outputs. The format below is how IndicBART was trained so the input should be "Sentence </s> <2xx>" where xx is the language code. Similarly, the output should be "<2yy> Sentence </s>". 
-inp = tokenizer("I am a boy </s> <2en>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids # tensor([[  466,  1981,    80, 25573, 64001, 64004]])
+# First tokenize the input. The format below is how IndicBART was trained so the input should be "Sentence </s> <2xx>" where xx is the language code. Similarly, the output should be "<2yy> Sentence </s>".
+inp = tokenizer("दिल्ली यूनिवर्सिटी देश की प्रसिद्ध यूनिवर्सिटी में से एक है. </s> <2hi>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids 
 
 # For generation. Pardon the messiness. Note the decoder_start_token_id.
-model.eval() # Set dropouts to zero
-model_output=model.generate(inp, use_cache=True,no_repeat_ngram_size=3,encoder_no_repeat_ngram_size=3, num_beams=4, max_length=20, min_length=1, early_stopping=True, pad_token_id=pad_id, bos_token_id=bos_id, eos_token_id=eos_id, decoder_start_token_id=tokenizer._convert_token_to_id_with_added_voc("<2en>"))
+
+model_output=model.generate(inp, use_cache=True,no_repeat_ngram_size=3,encoder_no_repeat_ngram_size=3, num_beams=4, max_length=20, min_length=1, early_stopping=True, pad_token_id=pad_id, bos_token_id=bos_id, eos_token_id=eos_id, decoder_start_token_id=tokenizer._convert_token_to_id_with_added_voc("<2hi>"))
+
 # Decode to get output strings
 decoded_output=tokenizer.decode(model_output[0], skip_special_tokens=True, clean_up_tokenization_spaces=False)
-print(decoded_output) # I am a boy
+print(decoded_output) # दिल्ली विश्वविद्यालय देश की प्रमुख विश्वविद्यालयों में शामिल है।
+
 # Note that if your output language is not Hindi or Marathi, you should convert its script from Devanagari to the desired language using the Indic NLP Library.
-# What if we mask?
-inp = tokenizer("I am [MASK] </s> <2en>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids
-model_output=model.generate(inp, use_cache=True,no_repeat_ngram_size=3,encoder_no_repeat_ngram_size=3, num_beams=4, max_length=20, min_length=1, early_stopping=True, pad_token_id=pad_id, bos_token_id=bos_id, eos_token_id=eos_id, decoder_start_token_id=tokenizer._convert_token_to_id_with_added_voc("<2en>"))
-decoded_output=tokenizer.decode(model_output[0], skip_special_tokens=True, clean_up_tokenization_spaces=False)
-print(decoded_output) # I am happy
-inp = tokenizer("मैं [MASK] हूँ </s> <2hi>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids
-model_output=model.generate(inp, use_cache=True,no_repeat_ngram_size=3,encoder_no_repeat_ngram_size=3, num_beams=4, max_length=20, min_length=1, early_stopping=True, pad_token_id=pad_id, bos_token_id=bos_id, eos_token_id=eos_id, decoder_start_token_id=tokenizer._convert_token_to_id_with_added_voc("<2en>"))
-decoded_output=tokenizer.decode(model_output[0], skip_special_tokens=True, clean_up_tokenization_spaces=False)
-print(decoded_output) # मैं जानता हूँ
-inp = tokenizer("मला [MASK] पाहिजे </s> <2mr>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids
-model_output=model.generate(inp, use_cache=True,no_repeat_ngram_size=3,encoder_no_repeat_ngram_size=3, num_beams=4, max_length=20, min_length=1, early_stopping=True, pad_token_id=pad_id, bos_token_id=bos_id, eos_token_id=eos_id, decoder_start_token_id=tokenizer._convert_token_to_id_with_added_voc("<2en>"))
-decoded_output=tokenizer.decode(model_output[0], skip_special_tokens=True, clean_up_tokenization_spaces=False)
-print(decoded_output) # मला ओळखलं पाहिजे
+
 ```
 # Note:
 If you wish to use any language written in a non-Devanagari script, then you should first convert it to Devanagari using the <a href="https://github.com/anoopkunchukuttan/indic_nlp_library">Indic NLP Library</a>. After you get the output, you should convert it back into the original script.