Spaces:
Running
Running
File size: 2,415 Bytes
83cfc4f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 |
import gradio as gr
import numpy as np
import scipy.io.wavfile as wavfile
import scipy.fft as fft
import yt_dlp
def fft_derivative(audio_data: np.ndarray, sample_rate: int) -> np.ndarray:
freq_domain = fft.fft(audio_data)
freqs = fft.fftfreq(len(audio_data), 1 / sample_rate)
freq_derivative = 1j * freqs * freq_domain
time_domain_derivative = fft.ifft(freq_derivative)
return np.real(time_domain_derivative)
def convert_file(audio_data: tuple[int, np.ndarray]) -> np.ndarray:
sample_rate, audio = audio_data
if len(audio.shape) == 2:
audio = np.mean(audio, axis=1)
derivative = fft_derivative(audio, sample_rate)
derivative = np.int16(derivative / np.max(np.abs(derivative)) * 32767)
return derivative
def process_audio_file(audio_file: str) -> tuple[int, np.ndarray]:
sample_rate, audio_data = wavfile.read(audio_file)
return sample_rate, audio_data
def process_youtube_link(youtube_link: str) -> str:
song_file = "downloaded_song.wav"
ydl_opts = {
'outtmpl': song_file.replace(".wav", ""),
'postprocessors': [{
'key': 'FFmpegExtractAudio',
'preferredcodec': 'wav',
}]
}
with yt_dlp.YoutubeDL(ydl_opts) as ydl:
ydl.download([youtube_link])
return song_file
def process_audio(audio: tuple[int, np.ndarray]) -> tuple[int, np.ndarray]:
return audio[0], convert_file(audio)
with gr.Blocks() as app:
with gr.Column():
youtube_link = gr.Textbox(label="YouTube Link", value="https://www.youtube.com/watch?v=YmJIccPWnEk")
download_button = gr.Button("Download")
audio_input = gr.Audio(label="Upload Audio File", type="numpy")
process_button = gr.Button("Process Audio")
audio_output = gr.Audio(label="Derivative Audio Output")
def download_audio(youtube_link: str):
song_file = process_youtube_link(youtube_link)
sample_rate, audio_data = process_audio_file(song_file)
return sample_rate, audio_data
def process_audio_input(audio):
sample_rate, processed_audio = process_audio(audio)
return sample_rate, processed_audio
download_button.click(download_audio, inputs=youtube_link, outputs=[audio_input])
process_button.click(process_audio_input, inputs=audio_input, outputs=audio_output)
if __name__ == "__main__":
app.launch()
|