app.py

import gradio as gr

from fastai.vision.all import *

from fastaudio.core.all import *

def get_x(df):
    return df.path
def get_y(df):
    return df.pattern
   
learn = load_learner('xresnet50_pitch3.pkl')

labels = learn.dls.vocab

def predict(Record, Upload):
    if Upload: path = Upload
    else: path = Record
    spec,pred,pred_idx,probs = learn.predict(str(path), with_input=True)

    return [{labels[i]: float(probs[i]) for i in range(len(labels))}, show_image(spec)]


title = "Japanese Pitch Accent Pattern Detector"

description = "This model will predict pitch accent pattern of a word based on the recording of its pronunciation."

article="<p style='text-align: center'><a href='mizoru.github.io/blog' target='_blank'>Blog</a></p>"

interpretation='default'

examples = [['代わる.mp3'],['大丈夫な.mp3'],['熱くない.mp3']]

enable_queue=True

gr.Interface(fn=predict,inputs=[gr.inputs.Audio(source='microphone', type='filepath', optional=True), gr.inputs.Audio(source='upload', type='filepath', optional=True)], outputs=  [gr.outputs.Label(num_top_classes=3), gr.outputs.Image(type="plot", label='Spectrogram')], title=title,description=description,article=article,examples=examples).launch(debug=True,share=True,enable_queue=enable_queue)