updated application file

app.py

@@ -1,21 +1,15 @@
 # -*- coding: utf-8 -*-
 
-import sys
 import crepe
-import spacy
 import librosa
-import subprocess
 import gradio as gr
 import pandas as pd
 from transformers import pipeline, RobertaTokenizerFast, TFRobertaForSequenceClassification
 
-subprocess.check_call([sys.executable, '-m', 'pip', 'install', 'https://huggingface.co/spacy/en_core_web_sm/resolve/main/en_core_web_sm-any-py3-none-any.whl'])
-
 asr = pipeline('automatic-speech-recognition', model='facebook/wav2vec2-large-960h-lv60-self')
 tokenizer = RobertaTokenizerFast.from_pretrained("arpanghoshal/EmoRoBERTa")
 model = TFRobertaForSequenceClassification.from_pretrained("arpanghoshal/EmoRoBERTa")
 emo = pipeline('sentiment-analysis', model='arpanghoshal/EmoRoBERTa')
-lang_model = spacy.load("spacy/en_core_web_sm")
 
 def transcribe_and_describe(audio):
 
@@ -23,10 +17,6 @@ def transcribe_and_describe(audio):
 
   text = asr(audio)['text']
 
-  doc = lang_model(text)
-  filler_words = [token.text for token in doc if token.pos_ == 'INTJ']
-  filler_word_pr =  len(filler_words) / len(doc)
-
   flatness = pd.DataFrame(librosa.feature.spectral_flatness(y=audio).T).describe().T
   loudness = pd.DataFrame(librosa.feature.rms(audio).T).describe().T
   time, frequency, confidence, activation = crepe.predict(audio, sr)
@@ -43,15 +33,14 @@ def transcribe_and_describe(audio):
 
   emotion = emo(text)[0]['label']
 
-  return (text, filler_word_pr, words_per_minute, mean_pitch, pitch_std, mean_volume, volume_std, mean_spectral_flatness, spectral_flatness_std,  emotion)
+  return (text, words_per_minute, mean_pitch, pitch_std, mean_volume, volume_std, mean_spectral_flatness, spectral_flatness_std,  emotion)
 
 gr.Interface(
     fn=transcribe_and_describe, 
     inputs=gr.Audio(source="microphone", type="filepath"), 
     outputs=[
-        gr.Text(label="Transcription"), 
+        gr.Text(label="Transcription"),
         gr.Text(label="Rate of Speech (WPM)"), 
-        gr.Text(label="Filler Word Percent"),
         gr.Text(label="Mean Pitch (Hz)"), 
         gr.Text(label="Pitch Variation (Hz)"), 
         gr.Text(label="Mean Volume (W)"),