JulianHerreilers/afrTTS

Afrikaans-based G2P and text-to-speech synthesis # afrTTS - Afrikaans PyTorch-based G2P and text-to-speech synthesis Welcome to afrTTS! We implement two systems: -NaiveTTS uses an existing limited pronunciation dictionary and suffers from misallignment. -G2PxTTS uses a G2P conversion model to expand this dictionary to create more coherent audio. Installs ```python pip install librosa pip install univoc pip install tacotron pip install omegaconf pip install torch ``` Tacotron A series pretrained weights are avaible at github.com only the following two should be used: -NaiveTTS: "github.com. -G2PxTTS: "github.com" Tacotron can be trained by running the following preprocessing and training commands: First adjust the first argument in line 32 of utils/jsonmaker.py to metadata_incomplete.csv then run the following commands: ```python python utils/jsonmaker.py python preprocess.py afrZA datasets/afrZA python train.py afrza afrZA/metadata_incomplete.csv datasets/afrZA ``` The G2P model can be trained and used to expand the pronuncation dictionary all from the notebook at G2P/G2P_LSTM.ipynb. A demo notebook afrTTS_demo.pynb can be used to test out the two systems provided that demo_utils.py, g2pmodel.py and the two dictionaries, afr_za_dict.txt and rcrl_apd.1.4.1.txt are in the same directory. Further datasets and alogrithms are available in utils/: -split_num_letters.py converts all numbers in a sequence to their word equivalents. -demo_sample_randomizer.ipynb was used to sort the demo samples for the subjective evaluation. -check_valid_entries complete.py returns the remainder of the dataset that remains in the selected dictionary, whether afr_za_dict.txt or rcrl_apd.1.4.1.txt. Acknowledegments: -github.com -https:/ …