$CUDA_VISIBLE_DEVICES=<gpu> python gvector_extraction.py <path-to-dataset-dir> --gvec_ckpt=<path-to-speaker-encoder-checkpoint> Train base synthesizer, first set the proper batch-size and gpu-numbers insynthesizer/hparams.py: # file: synthesizer/hprams.py tacotron_num_gpus = <n_gpus>, ...
This will generate scp files required by config.yaml (in the dataset/train section). You would also need to check that everything is fine in the config file. Usually you don't need to change the code. Now you can start your training by cd examples/aishell3 python ../../mtts/train....
This will generate scp files required by config.yaml (in the dataset/train section). You would also need to check that everything is fine in theconfig file. Usually you don't need to change the code. Now you can start your training by ...
Assume the path to the dataset is `~/datasets/data_aishell3`. Assume the path to the MFA result of AISHELL-3 is `./alignment`. Assume the path to the pretrained ge2e model is `ge2e_ckpt_path=./ge2e_ckpt_0.3/step-3000000` Assume the path to the MFA result of AISHELL-3 is `./...
This will generate scp files required by config.yaml (in the dataset/train section). You would also need to check that everything is fine in the config file. Usually you don't need to change the code. Now you can start your training by cd examples/aishell3 python ../../mtts/train....
This will generate scp files required by config.yaml (in the dataset/train section). You would also need to check that everything is fine in theconfig file. Usually you don't need to change the code. Now you can start your training by ...