Spaces:
Runtime error
Runtime error
File size: 3,885 Bytes
81adca3 49c39ca 952a6aa 49c39ca 952a6aa 49c39ca 952a6aa 49c39ca 952a6aa 49c39ca |
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 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 |
import os
os.system("pip install gradio==3.0.18")
from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification
import gradio as gr
import spacy
nlp = spacy.load('en_core_web_sm')
nlp.add_pipe('sentencizer')
def split_in_sentences(text):
doc = nlp(text)
return [str(sent).strip() for sent in doc.sents]
def make_spans(text,results):
results_list = []
for i in range(len(results)):
results_list.append(results[i]['label'])
facts_spans = []
facts_spans = list(zip(split_in_sentences(text),results_list))
return facts_spans
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):
resp = summarizer(text)
stext = resp[0]['summary_text']
return stext
##Fiscal Tone Analysis
fin_model= pipeline("sentiment-analysis", model='yiyanghkust/finbert-tone', tokenizer='yiyanghkust/finbert-tone')
def text_to_sentiment(text):
sentiment = fin_model(text)[0]["label"]
return sentiment
##Company Extraction
def fin_ner(text):
api = gr.Interface.load("dslim/bert-base-NER", src='models', use_auth_token=auth_token)
replaced_spans = api(text)
return replaced_spans
##Fiscal Sentiment by Sentence
def fin_ext(text):
results = fin_model(split_in_sentences(text))
return make_spans(text,results)
##Forward Looking Statement
def fls(text):
# fls_model = pipeline("text-classification", model="yiyanghkust/finbert-fls", tokenizer="yiyanghkust/finbert-fls")
fls_model = pipeline("text-classification", model="demo-org/finbert_fls", tokenizer="demo-org/finbert_fls", use_auth_token=auth_token)
results = fls_model(split_in_sentences(text))
return make_spans(text,results)
demo = gr.Interface()
with demo:
gr.Markdown("## Financial Analyst AI")
gr.Markdown("This project applies AI trained by our financial analysts to analyze earning calls and other financial documents.")
# Row 1: Speech Recognition and Text Summarization
with gr.Row():
with gr.Column():
audio_file = gr.inputs.Audio(source="microphone", type="filepath")
b1 = gr.Button("Recognize Speech")
text = gr.Textbox(value="") # Textbox for speech-to-text output
with gr.Column():
b2 = gr.Button("Summarize Text")
stext = gr.Textbox() # Textbox for summarized text output
# Row 2: Financial Tone Analysis
with gr.Row():
b3 = gr.Button("Classify Financial Tone")
label = gr.Label() # Label for sentiment analysis output
# Row 3: Financial Tone and Forward Looking Statement Analysis
with gr.Row():
b5 = gr.Button("Financial Tone and Forward Looking Statement Analysis")
fin_spans = gr.HighlightedText() # HighlightedText for financial sentiment spans
fls_spans = gr.HighlightedText() # HighlightedText for forward looking statement spans
# Row 4: Identify Companies & Locations
with gr.Row():
b4 = gr.Button("Identify Companies & Locations")
replaced_spans = gr.HighlightedText() # HighlightedText for named entity recognition spans
# Define the click handlers for the buttons
b1.click(speech_to_text, inputs=audio_file, outputs=text)
b2.click(summarize_text, inputs=text, outputs=stext)
b3.click(text_to_sentiment, inputs=stext, outputs=label)
b5.click(fin_ext, inputs=text, outputs=fin_spans)
b5.click(fls, inputs=text, outputs=fls_spans)
b4.click(fin_ner, inputs=text, outputs=replaced_spans)
demo.launch()
|