Upload MP3 to HF

create_ds.py

import json
from glob import glob
from os.path import basename

files_all = glob("data/*.mp3")

results = []
for idx, filename in enumerate(files_all):
    duration = 0
    results.append({'file_name': basename(filename), 'duration': duration, 'transcription': '-'})

with open('data/metadata.jsonl', 'w') as f:
  for result in results:
     f.write(json.dumps(result) + '\n')

upload_ds.py

from datasets import load_dataset

af_ds = load_dataset("audiofolder", data_dir="./data")

print(af_ds)

af_ds.push_to_hub("speech-uk/test-dataset", token='hf_....')