app.py

#!/usr/bin/env python
# coding: utf-8

# In[1]:


import gradio

from fastai.vision.all import *
from fastai.data.all import *
from pathlib import Path
import pandas as pd
from matplotlib.pyplot import specgram
import librosa
import librosa.display
from huggingface_hub import hf_hub_download
from fastai.learner import load_learner


# In[9]:


ref_file = hf_hub_download("gputrain/UrbanSound8K-model", "UrbanSound8K.csv")

model_file = hf_hub_download("gputrain/UrbanSound8K-model", "model.pkl")


# In[10]:


df = pd.read_csv(ref_file) 
df['fname'] = df[['slice_file_name','fold']].apply (lambda x: str(x['slice_file_name'][:-4])+'.png'.strip(),axis=1 )
my_dict = dict(zip(df.fname,df['class']))
def label_func(f_name):
    f_name = str(f_name).split('/')[-1:][0]
    return my_dict[f_name]
model = load_learner (model_file)
EXAMPLES_PATH = Path("./examples")
labels = model.dls.vocab


# In[11]:


with open("article.md") as f:
    article = f.read()


# In[12]:


interface_options = {
    "title": "Urban Sound 8K Classification",
    "description": "Fast AI example of using a pre-trained Resnet34 vision model for an audio classification task on the [Urban Sounds](https://urbansounddataset.weebly.com/urbansound8k.html) dataset. ",
    "article": article,
    "interpretation": "default",
    "layout": "horizontal",
    # Audio from validation file
    "examples": ["dog_bark.wav", "children_playing.wav", "air_conditioner.wav", "street_music.wav", "engine_idling.wav",
                "jackhammer.wav", "drilling.wav", "siren.wav","car_horn.wav","gun_shot.wav"],
    "allow_flagging": "never"
}


# In[13]:


def convert_sounds_melspectogram (audio_file):

    samples, sample_rate = librosa.load(audio_file)  #create onces with librosa

    fig = plt.figure(figsize=[0.72,0.72])
    ax = fig.add_subplot(111)
    ax.axes.get_xaxis().set_visible(False)
    ax.axes.get_yaxis().set_visible(False)
    ax.set_frame_on(False)
    melS = librosa.feature.melspectrogram(y=samples, sr=sample_rate)
    librosa.display.specshow(librosa.power_to_db(melS, ref=np.max))
    filename  = 'temp.png'
    plt.savefig(filename, dpi=400, bbox_inches='tight',pad_inches=0)
    plt.close('all')
    
    return None


# In[14]:


def predict():
    img = PILImage.create('temp.png')
    pred,pred_idx,probs = model.predict(img)
    return {labels[i]: float(probs[i]) for i in range(len(labels))}
    return labels_probs


# In[20]:


def end2endpipeline(filename):
    convert_sounds_melspectogram(filename)
    return predict()


# In[16]:


demo = gradio.Interface(
    fn=end2endpipeline,
    inputs=gradio.inputs.Audio(source="upload", type="filepath"),
    outputs=gradio.outputs.Label(num_top_classes=10),
    **interface_options,
)


# In[19]:


launch_options = {
    "enable_queue": True,
    "share": False,
    #"cache_examples": True,
}

demo.launch(**launch_options)


# In[ ]: