search

TensorSpeech / TensorFlowTTS

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
https://tensorspeech.github.io/TensorFlowTTS/
Apache License 2.0
3.85k stars 815 forks source link

Fastspeech Data preparation--- How to extract duration (duration_query (str): Query to find duration files in root_dir.) #746

Closed jeevan-revaneppa-hirethanad closed 2 years ago

jeevan-revaneppa-hirethanad commented 2 years ago

I'm unable to understand how to get 'duration_query (str): Query to find duration files in root_dir', while preparing data for training a fast speech model. It would be helpful if someone could suggest me how to proceed.

ttsking commented 2 years ago

you should first train a model of Tacotron2. then use the script of [extract_duration.py] (https://github.com/TensorSpeech/TensorFlowTTS/blob/master/examples/tacotron2/extract_duration.py) to generate duration files

stale[bot] commented 2 years ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs.