app.py

import gradio as gr
import torch
import torchaudio
from transformers import EncodecModel
from encodec.utils import convert_audio
from encodec import compress_to_file, decompress_from_file
import io

# Load the Encodec model 
model = EncodecModel.from_pretrained("facebook/encodec_48khz")
model.set_target_bandwidth(6.0)  # Set the desired bandwidth (adjust as needed)

@spaces.GPU
def encode(audio_file_path):
    try:
        # Load and pre-process the audio waveform
        wav, sr = torchaudio.load(audio_file_path)
        wav = convert_audio(wav, sr, model.sample_rate, model.channels)

        # Compress to ecdc file in memory
        output = io.BytesIO()
        compress_to_file(model, wav, output) 
        output.seek(0)

        return output

    except Exception as e:
        gr.Warning(f"An error occurred during encoding: {e}")
        return None

@spaces.GPU
def decode(compressed_audio_file):
    try:
        # Decompress audio
        wav, sr = decompress_from_file(compressed_audio_file)

        # Convert the decoded audio to a numpy array for Gradio output
        decoded_audio = wav.cpu().numpy() 

        return decoded_audio

    except Exception as e:
        gr.Warning(f"An error occurred during decoding: {e}")
        return None

# Gradio interface
with gr.Blocks() as demo:
    gr.Markdown("<h1 style='text-align: center;'>Audio Compression with Encodec</h1>")

    with gr.Tab("Encode"):
        with gr.Row():
            audio_input = gr.Audio(type="filepath", label="Input Audio")
            encode_button = gr.Button("Encode", variant="primary")
        with gr.Row():
            encoded_output = gr.File(label="Compressed Audio (.ecdc)")

        encode_button.click(encode, inputs=audio_input, outputs=encoded_output)

    with gr.Tab("Decode"):
        with gr.Row():
            compressed_input = gr.File(label="Compressed Audio (.ecdc)")
            decode_button = gr.Button("Decode", variant="primary")
        with gr.Row():
            decoded_output = gr.Audio(label="Decompressed Audio")

        decode_button.click(decode, inputs=compressed_input, outputs=decoded_output)

demo.queue().launch()