app.py

import gradio as gr
from transformers import pipeline

transcription = pipeline("automatic-speech-recognition", model="facebook/wav2vec2-base-100h")
clasification = pipeline(
    "audio-classification",
    model="anton-l/xtreme_s_xlsr_300m_minds14",
)

def audio_a_text(audio):
  text = transcription(audio)["text"]
  return text

def text_to_sentimient(audio):
    text = transcription(audio)["text"]
    return clasification(text)[0]["label"]

demo = gr.Blocks()

with demo:
  gr.Markdown("Speech analyzer")
  audio = gr.Audio(type="filepath", label = "Upload a file")
  text = gr.Textbox()
  b1 = gr.Button("convert to text")
  b1.click(audio_a_text, inputs=audio, outputs=text)

  b2 = gr.Button("Classification of speech")
  b2.click(text_to_sentimient, inputs=audio, outputs=text)

demo.launch()