app.py

import gradio as gr
import librosa
from transformers import AutoFeatureExtractor, pipeline


def load_and_fix_data(input_file, model_sampling_rate):
    speech, sample_rate = librosa.load(input_file)
    if len(speech.shape) > 1:
        speech = speech[:, 0] + speech[:, 1]
    if sample_rate != model_sampling_rate:
        speech = librosa.resample(speech, sample_rate, model_sampling_rate)
    return speech

#Loading the feature extractor and instantiating the pipeline by launching pipeline()
model_name1 = "jonatasgrosman/wav2vec2-xls-r-1b-spanish"
feature_extractor = AutoFeatureExtractor.from_pretrained(model_name1)
sampling_rate = feature_extractor.sampling_rate
asr = pipeline("automatic-speech-recognition", model=model_name1)

#Instantiating a pipeline for classifying the text
model_name2 = "hackathon-pln-es/twitter_sexismo-finetuned-robertuito-exist2021"
classifier = pipeline("text-classification", model = model_name2)

#Defining a function for speech-to_text conversion
def speech_to_text(input_file):
    speech = load_fix_data(input_file, sampling_rate)
    transcribed_text = asr(speech, chunk_length_s=15, stride_length_s=1)["text"]
    return transcribed_text

#Defining a function for sexism detection        
def sexism_detection(transcribed_text):
    sexism_detection = classifier(transcribed_text)[0]["label"]
    return sexism_detection

#Defining a function which will output Spanish audio transcription and the detected sentiment
def asr_and_sexism_detection(input_file):
    transcribed_text = speech_to_text(input_file)
    sexism_detection = sexism_detection(transcribed_text)
    if sexism_detection == "LABEL_0":
        return "The input audio contains NON-SEXIST language"
    else:
        return "SEXIST LANGUAGE DETECTED"


description = """ This is a Gradio demo for Spanish audio transcription-based Sexism detection. The key objective is to detect whether the sexist language is present in the audio or not. To use this app, simply provide an audio input (audio recording or via microphone), which will subsequently be transcribed and classified as sexism/non-sexism pertaining to audio (transcription) with the help of pre-trained models.



**Note regarding the predicted label: LABEL_0: "NON SEXISM" or LABEL_1: "SEXISM"**



Pre-trained Model used for Spanish ASR: [jonatasgrosman/wav2vec2-xls-r-1b-spanish](https://huggingface.co/jonatasgrosman/wav2vec2-xls-r-1b-spanish)

Pre-trained Model used for Sexism Detection : [hackathon-pln-es/twitter_sexismo-finetuned-robertuito-exist2021](https://huggingface.co/hackathon-pln-es/twitter_sexismo-finetuned-robertuito-exist2021)

"""


gr.Interface(
    asr_and_sexism_detection,
    inputs=[gr.inputs.Audio(source="microphone", type="filepath", label="Record your audio")],
    #outputs=[gr.outputs.Label(num_top_classes=2),gr.outputs.Label(num_top_classes=2), gr.outputs.Label(num_top_classes=2)],
    outputs=[gr.outputs.Textbox(label="Predicción")],
    examples=[["audio1.wav"], ["audio2.wav"], ["audio3.wav"], ["audio4.wav"], ["sample_audio.wav"]],
    title="Spanish-Audio-Transcription-based-Sexism-Detection",
    description=description,
    layout="horizontal",
    theme="huggingface",
).launch(enable_queue=True)