Data/add.py

#!/usr/bin/env python3

INPUT_FILE = "fashion_train.txt"
OUTPUT_FILE = "fashion.txt"

def main():
    out_lines = []
    with open(INPUT_FILE, "r", encoding="utf-8") as f:
        for line in f:
            line = line.rstrip("\n")
            if not line.strip():
                continue

            parts = line.split("|")
            # Expecting: path | phonemes | speaker_id | text
            if len(parts) == 4:
                path, phonemes, speaker_id, text = parts
                new_line = f"{path}|{phonemes}|{speaker_id}|0|{text}"
                out_lines.append(new_line)
            else:
                # If unexpected format, keep line as-is
                out_lines.append(line)

    with open(OUTPUT_FILE, "w", encoding="utf-8") as f:
        for l in out_lines:
            f.write(l + "\n")

    print(f"✅ Added language column successfully → {OUTPUT_FILE}")

if __name__ == "__main__":
    main()