search

rhasspy / piper

A fast, local neural text to speech system
https://rhasspy.github.io/piper-samples/
MIT License
6.19k stars 453 forks source link

Error while pre-processing #220

Open abcnm123456 opened 1 year ago

abcnm123456 commented 1 year ago

WhatsApp Image 2023-09-22 at 20 29 46 (.venv) user@DESKTOP-U00B88J:~/piper/src/python$ python -m piper_train.preprocess --input-dir ~/piper/DATASET/GoogleSmall --output-dir ~/piper/TRAINED --language en --sample-rate 16000 --dataset-format ljspeech INFO:preprocess:Single speaker dataset INFO:preprocess:Wrote dataset config INFO:preprocess:Processing 4 utterance(s) with 16 worker(s) Traceback (most recent call last): File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/usr/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/home/user/piper/src/python/piper_train/preprocess.py", line 473, in main() File "/home/user/piper/src/python/piper_train/preprocess.py", line 202, in main for utt_batch in batched( File "/home/user/piper/src/python/piper_train/preprocess.py", line 462, in batched raise ValueError("n must be at least one") ValueError: n must be at least one

rmcpantoja commented 1 year ago

Hi @abcnm123456, Your dataset is too short. For fine-tuning, requires minimum 5 minutes of data to work better.