scripts/create_training_file.py

import json
import os
from pathlib import Path

def create_training_file():
    json_dir = Path("/root/piper_msa/Json_dic")
    audio_base_dir = Path("/root/piper_msa/raw_audio")
    output_file = Path("/root/piper_msa/training_data.csv")
    
    training_lines = []
    
    # Process each speaker (SPK1 to SPK5)
    for spk_num in range(1, 6):
        json_file = json_dir / f"SPK{spk_num}_phoneme_data.json"
        audio_dir = audio_base_dir / f"SPK{spk_num}"
        
        if not json_file.exists():
            print(f"Warning: {json_file} not found, skipping...")
            continue
            
        if not audio_dir.exists():
            print(f"Warning: {audio_dir} not found, skipping...")
            continue
        
        # Read JSON file
        with open(json_file, 'r', encoding='utf-8') as f:
            data = json.load(f)
        
        # Process each sample
        for sample in data.get('train_samples', []):
            audio_file = sample.get('audio_file')
            text = sample.get('text')
            
            if audio_file and text:
                # Add .wav extension if not present
                if not audio_file.endswith('.wav'):
                    audio_file = f"{audio_file}.wav"
                
                # Construct full audio path
                audio_path = audio_dir / audio_file
                
                # Check if audio file exists
                if audio_path.exists():
                    # Format: /full/path/to/audio.wav|Text content
                    line = f"{audio_path}|{text}"
                    training_lines.append(line)
                else:
                    print(f"Warning: Audio file not found: {audio_path}")
        
        print(f"Processed SPK{spk_num}: {len(data.get('train_samples', []))} samples")
    
    # Write to output file in CSV format (pipe-separated)
    with open(output_file, 'w', encoding='utf-8') as f:
        f.write('\n'.join(training_lines))
    
    print(f"\nTraining file created: {output_file}")
    print(f"Total samples: {len(training_lines)}")
    
    return output_file, len(training_lines)

if __name__ == "__main__":
    output_file, total_samples = create_training_file()
    print(f"\nDone! Created {output_file} with {total_samples} training samples.")