Merge branch 'main' of https://huggingface.co/spaces/gabrielanicole/literacy

app.py

@@ -71,9 +71,11 @@ dict_tokenizer_tr = {
 	'en-sw': tokenizer_sw,
 }
 
-dict_reference_faiss = {
-	'en-es': load_index('en-es'),
-}
+# dict_reference_faiss = {
+# 	'en-es': load_index('en-es'),
+# }
+
+# print("dict", dict_reference_faiss['en-es']['input']['tokens'][1])
 
 saliency_examples = [
 	"Peace of Mind: Protection for consumers.",
@@ -753,7 +755,7 @@ def first_function(w1, model):
 			# 'texts' : 	dict_tokenizer_tr[model].decode(params[1].sequences.tolist())
 		})
 	
-	## load_reference; 
+	## load_reference; ERROR 
 	## Build FAISS index 
 	# ---> preload faiss using the respective model with a initial dataset. 
 	## dict_reference_faiss[model] = metadata_all [per language]
@@ -763,22 +765,25 @@ def first_function(w1, model):
 
 	## Build FAISS index 
 	# ---> preload faiss using the respective model with a initial dataset. 
-	result_search = {}
-	result_search['input'] = build_search(input_embeddings, model, type='input')
-	result_search['output'] = build_search(output_embeddings, model, type='output')
-
-	json_out = {'input': {'tokens': {}, 'words': {}}, 'output': {'tokens': {}, 'words': {}}}
-	dict_projected = {}
-	for type in ['input', 'output']:
-		dict_projected[type] = {} 
-		for key in ['tokens', 'words']: 
-			similar_key = result_search[type][key]['similar']
-			vocab = result_search[type][key]['vocab_queries']
-			dict_projected[type][key] =  filtered_projection(similar_key, vocab, model, type=type, key=key)
-			json_out[type][key]['similar_queries'] = similar_key
-			json_out[type][key]['tnse'] = dict_projected[type][key]
-			json_out[type][key]['key_text_list'] = result_search[type][key]['sentence_key_list']
 
+    ### to uncomment gg1 ###
+	# result_search = {}
+	# result_search['input'] = build_search(input_embeddings, model, type='input')
+	# result_search['output'] = build_search(output_embeddings, model, type='output')
+
+	# json_out = {'input': {'tokens': {}, 'words': {}}, 'output': {'tokens': {}, 'words': {}}}
+	# dict_projected = {}
+	# for type in ['input', 'output']:
+	# 	dict_projected[type] = {} 
+	# 	for key in ['tokens', 'words']: 
+	# 		similar_key = result_search[type][key]['similar']
+	# 		vocab = result_search[type][key]['vocab_queries']
+	# 		dict_projected[type][key] =  filtered_projection(similar_key, vocab, model, type=type, key=key)
+	# 		json_out[type][key]['similar_queries'] = similar_key
+	# 		json_out[type][key]['tnse'] = dict_projected[type][key]
+	# 		json_out[type][key]['key_text_list'] = result_search[type][key]['sentence_key_list']
+    ### to uncomment gg1 ### 
+    
 	## bertviz
 	# paramsbv, tgtbv = get_bertvis_data(w1, model)
 	
@@ -787,8 +792,11 @@ def first_function(w1, model):
 	html_att_dec = params[3][1]
 	html_att_cross = params[4][1]
 	
-
-	params = [params[0], params[1], json_out, params[2][0], params[3][0], params[4][0]]
+    ### to uncomment gg1 ###
+	# params = [params[0], params[1], json_out, params[2][0], params[3][0], params[4][0]]
+    ### to uncomment gg1 ###
+    
+	params = [params[0], params[1], [], params[2][0], params[3][0], params[4][0]]
 	# params.append([tgt, params['params'], params['html2'].data]
 
 	return [translated_text, params, html_att_enc, html_att_dec, html_att_cross]

pre-requirements.txt

@@ -0,0 +1 @@
+faiss-cpu==1.8.0

requirements.txt

@@ -1,4 +1,4 @@
-bertviz
-jupyter
-scikit-learn
-faiss-cpu
+bertviz
+jupyter
+scikit-learn
+faiss-cpu==1.8.0.post1