model_script/script/tts_test.py

from pathlib import Path
from typing import List, Dict, Any

import pandas as pd

from util import file_util

base_dir = "/Users/zhao/Desktop/tzld/TTS"

test_sample_csv = f"{base_dir}/test_sample.csv"
reference_path = f"{base_dir}/audio"


def read_test_sample(csv_file: Path) -> List[Dict[str, Any]]:
    if csv_file.exists():
        df = pd.read_csv(csv_file)
        return df.to_dict(orient="records")
    else:
        return []


def reference_audio_download(audio_url: str, local_file_path: str):
    file_util.download_file(audio_url, local_file_path)


def main():
    df = pd.read_csv(test_sample_csv)

    speaker_counts = df["speaker"].value_counts()
    print(f"{'speaker':<30} count")
    print("-" * 38)
    for speaker, count in speaker_counts.items():
        print(f"{speaker:<30} {count}")

    # test_sample_list = read_test_sample(Path(test_sample_csv))
    # for item in test_sample_list:
    #     speaker = item["speaker"]
    #     audio_url = item["audio_url"]
    #     result = item["result"]
    #     txt = item["txt"]
    #     reference_audio_download(audio_url, local_file_path=f"{reference_path}/{speaker}.mp3")


if __name__ == '__main__':
    main()