search

keonlee9420 / Expressive-FastSpeech2

PyTorch Implementation of Non-autoregressive Expressive (emotional, conversational) TTS based on FastSpeech2, supporting English, Korean, and your own languages.
Other
267 stars 46 forks source link

iemocap-aligner.zip not found? #21

Open ZayneHuang opened 11 months ago

ZayneHuang commented 11 months ago

Hi author @keonlee9420 ,

Thanks for your repository, which is very useful to my project. However, I met some problem in trying to use a continuous model (following the README in continuous branch). When I am aligning the data with MFA using pre-trained models: mfa align ./raw_data/IEMOCAP/sessions lexicon/iemocap-lexicon.txt montreal-forced-aligner/iemocap-aligner.zip preprocessed_data/IEMOCAP/TextGrid --speaker_characters prosodylab -j 8 --clean The program raised error:

FileArgumentNotFoundError: Could not find "montreal-forced-aligner/iemocap-aligner.zip"

It seems that iemocap-aligner.zip is not found in the path. However, this zip file is required by MFA as ACOUSTIC_MODEL_PATH. The version of MFA is 2.0.6, which is installed by conda create -n aligner -c conda-forge montreal-forced-aligner=2.0.6 praatio=5.1.1 sqlalchemy=1.4.3 as instructed by MFA document and issue.

Do you have any idea on how to fetch the iemocap-aligner.zip file? I cannot find it anywhere.

Thank you so much, and I'll patiently await your kind response.