app.py

import os
import numpy as np
import gradio as gr
from gradio.mix import Series
from transformers import pipeline

path_to_L_model = str(os.environ['path_to_L_model'])
read_token      = str(os.environ['read_token'])

description = "Talk to Breud!"
title       = "Breud (BERT + Freud)"

# wisper = gr.Interface.load("models/openai/whisper-base")

# interface_model_L = gr.Interface.load(
#             name=path_to_L_model,
#             api_key=read_token,
# )

# Series( 
#     wisper, 
#     interface_model_L,
#     description = description,
#     title = title,
#     inputs = gr.Audio(source="microphone"),
# ).launch()


asr = pipeline("automatic-speech-recognition", "openai/whisper-base")
classifier = pipeline("text-classification", path_to_L_model, api_token=read_token)


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


def text_to_sentiment(text):
    return classifier(text)[0]["label"]


demo = gr.Blocks()

with demo:
    audio_file = gr.Audio(source="microphone")
    text = gr.Textbox()
    label = gr.Label()

    b1 = gr.Button("Recognize Speech")
    b2 = gr.Button("Classify Sentiment")

    b1.click(speech_to_text, inputs=audio_file, outputs=text)
    b2.click(text_to_sentiment, inputs=text, outputs=label)

demo.launch()