app.py

#IMPORT THE LIBRARIES
import pandas as pd
import numpy as np
import joblib
import os
import sys

# librosa is a Python library for analyzing audio and music. It can be used to extract the data from the audio files we will see it later.
import librosa
import librosa.display
import seaborn as sns
import matplotlib.pyplot as plt

from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.metrics import confusion_matrix, classification_report
from sklearn.model_selection import train_test_split

# to play the audio files


import keras
from keras.preprocessing import sequence
from keras.models import Sequential,model_from_json
from keras.layers import Dense, Embedding
from keras.layers import LSTM,BatchNormalization , GRU
from keras.preprocessing.text import Tokenizer

from tensorflow.keras.utils import to_categorical
from keras.layers import Input, Flatten, Dropout, Activation
from keras.layers import Conv1D, MaxPooling1D, AveragePooling1D
from keras.models import Model
from keras.callbacks import ModelCheckpoint
from tensorflow.keras.optimizers import SGD



import warnings
if not sys.warnoptions:
    warnings.simplefilter("ignore")
warnings.filterwarnings("ignore", category=DeprecationWarning)
import tensorflow as tf 
from huggingface_hub import from_pretrained_keras
import gradio as gr
from huggingface_hub import from_pretrained_keras
model=from_pretrained_keras( 'Mohamed41/MODEL_EMOTION_AR_TEXT_72P')  

def feat_ext(data):
    #Time_domain_features
    # ZCR Persody features or Low level ascoustic features
    result = np.array([])
    zcr = np.mean(librosa.feature.zero_crossing_rate(y=data).T, axis=0)
    result=np.hstack((result, zcr)) # stacking horizontally
    #Frequency_domain_features
    #Spectral and wavelet Features
    #MFCC
    mfcc = np.mean(librosa.feature.mfcc(y=data, sr=22050,n_mfcc=40).T, axis=0)
    result = np.hstack((result, mfcc)) # stacking horizontally
    return result


scaler = joblib.load('scaler.joblib')
encoder= joblib.load('encoder.joblib')  

def get_predict_feat(path):
    d, s_rate= librosa.load(path, duration=2.5, offset=0.6)
    res=feat_ext(d)
    result=np.array(res)
    result=np.reshape(result,newshape=(1,41))
    i_result = scaler.transform(result)
    final_result=np.expand_dims(i_result, axis=2)
    
    return final_result  

emotions1={1:'Neutral', 2:'Calm', 3:'Happy', 4:'Sad', 5:'Angry', 6:'Fear', 7:'Disgust',8:'Surprise'}
def prediction(path1):
    res=get_predict_feat(path1)
    predictions=model.predict(res)
    y_pred = encoder.inverse_transform(predictions)
    return y_pred[0][0]    
def mainfunc(data):
   print(data)
   return  str(data)
audio_input = gr.inputs.Audio(type="filepath")
iface = gr.Interface(fn=mainfunc, inputs=audio_input, outputs="text")
iface.launch(inline=False)