diff --git a/src/embed_text_package/embed_text.py b/src/embed_text_package/embed_text.py index 2667d5c..8a6e650 100644 --- a/src/embed_text_package/embed_text.py +++ b/src/embed_text_package/embed_text.py @@ -3,6 +3,7 @@ """ import torch +from tqdm import tqdm def get_embeddings(sentence_batches: list, model, tokenizer): @@ -31,7 +32,8 @@ def get_embeddings(sentence_batches: list, model, tokenizer): emb_batches = [] - for batch in sentence_batches: + for batch in tqdm(sentence_batches, + ascii=True, desc="Embedding Batches..."): batch_emb = [] for sentence in batch: # 1) Get Tokens of sentence