multilingual-22-12

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("CohereLabs/multilingual-22-12")
text = "Hellö World, this is my input string!"
enc = tokenizer(text)
print("Encoded input:")
print(enc)

inv_vocab = {v: k for k, v in tokenizer.vocab.items()}
tokens = [inv_vocab[token_id] for token_id in enc['input_ids']]
print("Tokens:")
print(tokens)

number_of_tokens = len(enc['input_ids'])
print("Number of tokens:", number_of_tokens)