VoiceCraft icon indicating copy to clipboard operation
VoiceCraft copied to clipboard

File Not Found Error when running ./data/phonemize_encodec_encode_hf.py file

Open AroonSankoh opened this issue 1 year ago • 1 comments

I'm trying to train my own voice craft model but am encountering an issue when running the following script:

python phonemize_encodec_encode_hf.py --dataset_size xs \ --download_to path/to/store_huggingface_downloads \ --save_dir path/to/store_extracted_codes_and_phonemes \
--encodec_model_path ~/VoiceCraft/pretrained_models/encodec_4cb2048_giga.th
--mega_batch_size 120
--batch_size 32
--max_len 30000 \

This is my output, I'm not sure what file the load_dataset call is looking for. Screen Shot 2024-06-04 at 12 47 28 PM

AroonSankoh avatar Jun 04 '24 16:06 AroonSankoh

https://huggingface.co/datasets/speechcolab/gigaspeech

jasonppy avatar Jun 09 '24 18:06 jasonppy