app.py

import gradio as gr
import librosa
import os
import spaces
from pathlib import Path
from pytorch.inference import PianoTranscription
from utils import config
# from synthviz import create_video # TODO enable video rendering
from midi2audio import FluidSynth

RESULTS_DIR='results'

# Initialize the transcriptor
transcriptor = PianoTranscription("Note_pedal")

# Soundfont
soundfont_path = "soundfont/MuseScore_General.sf3"
fs = FluidSynth(soundfont_path)

@spaces.GPU
def transcribe_and_visualize(audio_file):
    # Generate a unique filename for the MIDI and video outputs
    # base_name = os.path.splitext(os.path.basename(audio_file.name))[0]
    base_name = os.path.splitext(os.path.basename(audio_file))[0]
    midi_filename = f"{base_name}_transcription.mid"
    # video_filename = f"{base_name}_output.mp4" # TODO enable video rendering
    flac_filename = f"{base_name}_transcription.flac"
    
    # Load and transcribe audio
    audio, _ = librosa.core.load(audio_file, sr=config.sample_rate)
    transcriptor.transcribe(audio, midi_filename)
    
    # Create visualization video
    # create_video(input_midi=midi_filename, video_filename=video_filename) # TODO enable video rendering

    # Convert MIDI to FLAC
    fs.midi_to_audio(midi_filename, flac_filename)

    # Return midi
    return flac_filename, midi_filename

# Create Gradio interface
iface = gr.Interface(
    fn=transcribe_and_visualize,
    inputs=gr.Audio(type="filepath", label="Upload Piano Audio"),
    # outputs=gr.Video(label="Transcription Visualization"),
    outputs=[gr.Audio(label="MIDI transcription"), gr.File(label="MIDI file")],
    title="MOZART - AI Piano Transcriber",
    description="Gradio-based piano transcriber, using Bytedance's Piano Transcription AI model. Upload a piano audio file to transcribe it into a MIDI file. Open in a piano roll app like Synthesia to see the magic.",
)

# Launch the interface
iface.launch()