-
2020
-
Live Demo on Google Colab
-
Deepstory – major update
-
Waiting for Godot
-
Deepstory – memory issue
-
Deepstory – Web interface and Flask
-
Deepstory – jQuery
-
Deepstory – GPT-2 and transformers
-
Deepstory – Speech-driven animation to first-order model
-
Deepstory – Synthesize in Voice class and combine audio arrays
-
Deepstory – Text normalization
-
HDF5, h5py, Zarr for packing pre-processed audio data
-
Errors, unexpected result and packing files
-
Tool – Audio batch pre-processing and manual checking
-
Normalize silences in audios
-
Why I haven’t thought about that?
-
Deepspeech and Audio segmentation
-
Audio pre-processing
-
Tweaking TTS model for increased precision
-
Training GPT-2
-
Tool – Witcher books data extraction
-
VOCA and synthesized audio
-
Discovering transfer learning
-
Tensorboard and training
-
Accident & new discoveries
-
Speech driven animation and VOCA
-
Amazing results, big progress
-
Frustrations and surprise
-
Tool – Data/Text pre-processing
-
Tool – Extracting audio files
-
Animate still image with first order model