File size: 2,677 Bytes
eed3dce ff39d68 4240a50 560a994 58b2731 ff39d68 560a994 ff39d68 560a994 d250ad6 560a994 6f488a4 ff39d68 c6df2b8 ff39d68 560a994 d26fdac 88a4d3b 3c577a6 6f488a4 d4f0f2b 58b2731 6f488a4 560a994 ca24370 560a994 b29c07d ca24370 7ea20fe 560a994 7ea20fe 560a994 ca24370 560a994 ff39d68 35b1732 ff39d68 35b1732 ff39d68 a212991 d250ad6 564ec1c d250ad6 560a994 35b1732 d250ad6 ff39d68 0e1f235 f5dc180 6f488a4 0e1f235 560a994 722ae5b 560a994 358709b |
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 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 |
from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification
import gradio as gr
import os
import spacy
nlp = spacy.load('en_core_web_sm')
auth_token = os.environ.get("HF_Token")
##Speech Recognition
asr = pipeline("automatic-speech-recognition", "facebook/wav2vec2-base-960h")
def transcribe(audio):
text = asr(audio)["text"]
return text
def speech_to_text(speech):
text = asr(speech)["text"]
return text
##Summarization
summarizer = pipeline("summarization", model="knkarthick/MEETING_SUMMARY")
def summarize_text(text):
stext = summarizer(text)
return stext
##Fiscal Sentiment
fin_model = pipeline("text-classification", model="demo-org/auditor_review_model", \
tokenizer="demo-org/auditor_review_model",use_auth_token=auth_token)
def text_to_sentiment(text):
sentiment = fin_model(text)[0]["label"]
return sentiment
##Company Extraction
def fin_ner(text):
print ("ner")
#ner_pipeline = pipeline("ner", model="dslim/bert-base-NER", tokenizer="dslim/bert-base-NER")
api = gr.Interface.load("dslim/bert-base-NER", src='models')
replaced_spans = api(text)
print (replaced_spans)
print ("spans2")
#replaced_spans = [(key, None) if value=='No Disease' else (key, value) for (key, value) in spans]
return replaced_spans
##Fiscal Sentiment by Sentence
def fin_ext(text):
print ("sent")
doc = nlp(text)
doc_sents = [sent for sent in doc.sents]
sents_list = []
for sent in doc.sents:
sents_list.append(sent.text)
results = fin_model(sents_list)
print (results)
results_list = []
for i in range(len(results)):
results_list.append(results[i]['label'])
fin_spans = []
fin_spans = list(zip(sents_list,results_list))
print (fin_spans)
return fin_spans
demo = gr.Blocks()
with demo:
audio_file = gr.inputs.Audio(source="microphone", type="filepath")
b1 = gr.Button("Recognize Speech")
text = gr.Textbox()
b1.click(speech_to_text, inputs=audio_file, outputs=text)
b2 = gr.Button("Summarize Text")
stext = gr.Textbox()
b2.click(summarize_text, inputs=text, outputs=stext)
b3 = gr.Button("Classify Overall Financial Sentiment")
label = gr.Label()
b3.click(text_to_sentiment, inputs=stext, outputs=label)
b4 = gr.Button("Extract Companies & Segments")
replaced_spans = gr.HighlightedText()
b4.click(fin_ner, inputs=text, outputs=replaced_spans)
b5 = gr.Button("Extract Financial Sentiment")
fin_spans = gr.HighlightedText()
b5.click(fin_ext, inputs=text, outputs=fin_spans)
demo.launch() |