Spaces:
Runtime error
Runtime error
File size: 2,349 Bytes
9543aec 54c0de7 9543aec 6f6865f 9543aec cc063db 9543aec 06b480a 9543aec 5c4bbd0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 |
import gradio as gr
import json
from sentence_transformers import SentenceTransformer, InputExample, util
import pandas as pd
def Main(Modelo, Texto1, Texto2):
error = ""
modelResult = ""
try:
data_test = []
data_test.append(InputExample(guid= "", texts=[Texto1, Texto2], label=0))
modelResult = TestModel('jfarray/Model_'+ Modelo +'_50_Epochs',data_test)
except Exception as e:
error = e
return [error, modelResult]
def TestModel(checkpoint, data):
local_model_path = checkpoint
model = SentenceTransformer(local_model_path)
df = pd.DataFrame(columns=["Similitud Semántica"])
sentences1 = []
sentences2 = []
hashed_ids = []
marks = []
scores = []
for i in range (0,len(data)): #len(data)
sentences1.append(data[i].texts[0])
sentences2.append(data[i].texts[1])
#Compute embedding for both lists
embeddings1 = model.encode(sentences1, convert_to_tensor=True)
embeddings2 = model.encode(sentences2, convert_to_tensor=True)
#Compute cosine-similarits
cosine_scores = util.cos_sim(embeddings1, embeddings2)
for i in range(len(sentences1)):
hashed_ids.append(data[i].guid)
marks.append(data[i].label)
scores.append(round(cosine_scores[i][i].item(),3))
df['Similitud Semántica'] = scores
return df
Modelos = gr.inputs.Dropdown(["dccuchile_bert-base-spanish-wwm-uncased"
, "bert-base-multilingual-uncased"
, "all-distilroberta-v1"
, "paraphrase-multilingual-mpnet-base-v2"
, "paraphrase-multilingual-MiniLM-L12-v2"
, "distiluse-base-multilingual-cased-v1"])
Opciones = gr.inputs.Radio(["Comparar Textos", "Procesar Fichero"])
Text1Input = gr.inputs.Textbox(lines=10, placeholder="Escriba el texto aqui ...")
Text2Input = gr.inputs.Textbox(lines=10, placeholder="Escriba el otro texto aqui ...")
LabelOutput = gr.outputs.Label(num_top_classes=None, type="auto", label="")
DataFrameOutput = gr.outputs.Dataframe(headers=["Similitud Semántica"]
, max_rows=20, max_cols=None, overflow_row_behaviour="paginate", type="pandas", label="Resultado")
iface = gr.Interface(fn=Main
, inputs=[ Modelos, Text1Input ,Text2Input]
, outputs=[LabelOutput, DataFrameOutput]
, title = "Similitud Semántica de textos en Español de tamaño medio (200-250 palabras)"
)
iface.launch(share = False,enable_queue=True, show_error =True) |