File size: 1,438 Bytes
7a7ebdf
ff39d68
4240a50
ff39d68
 
d250ad6
d02f0ba
 
 
 
 
35b1732
ff39d68
 
 
 
 
 
 
 
d250ad6
 
 
 
ff39d68
d02f0ba
ff39d68
 
 
 
 
35b1732
ff39d68
35b1732
ff39d68
a212991
 
d250ad6
564ec1c
 
d250ad6
 
35b1732
d250ad6
ff39d68
 
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
from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
import gradio as gr
import os

asr = pipeline("automatic-speech-recognition", "facebook/wav2vec2-base-960h")
summarizer = pipeline("summarization", model="knkarthick/MEETING_SUMMARY")

auth_token = os.environ.get("HF_Token")
tokenizer = AutoTokenizer.from_pretrained("demo-org/auditor_review_model",use_auth_token=auth_token)
audit_model = AutoModelForSequenceClassification.from_pretrained("demo-org/auditor_review_model",use_auth_token=auth_token)
nlp = pipeline("text-classification", model=audit_model, tokenizer=tokenizer)

def transcribe(audio):
    text = asr(audio)["text"]
    return text

def speech_to_text(speech):
    text = asr(speech)["text"]
    return text

def summarize_text(text):
    stext = summarizer(text)
    return stext

def text_to_sentiment(text):
    sentiment = nlp(text)[0]["label"]
    return sentiment 
    
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 Sentiment")
    label = gr.Label()
    b3.click(text_to_sentiment, inputs=stext, outputs=label)
    
demo.launch(share=True)