Eren Gölge
a0a9279e4b
commit 212d330929c22d0cd970be2023770dc1e39449ab
Author: Edresson Casanova <edresson1@gmail.com>
Date: Fri Apr 29 16:29:44 2022 -0300
Fix unit test
commit 44456b0483bf42b1337a8e408ac17af38b26b1fa
Author: Edresson Casanova <edresson1@gmail.com>
Date: Fri Apr 29 07:28:39 2022 -0300
Fix style
commit d545beadb932758eb7d1c632778fe317d467a6a4
Author: Edresson Casanova <edresson1@gmail.com>
Date: Thu Apr 28 17:08:04 2022 -0300
Change order of HIFI-GAN optimizers to be equal than the original repository
commit 657c5442e5339581e5c09168f5212112a342d97a
Author: Edresson Casanova <edresson1@gmail.com>
Date: Thu Apr 28 15:40:16 2022 -0300
Remove audio padding before mel spec extraction
commit 76b274e6901495ffe62ec745fd8ca9fd010f4857
Merge: 379ccd7b 6233f4fc
Author: Edresson Casanova <edresson1@gmail.com>
Date: Wed Apr 27 07:28:48 2022 -0300
Merge pull request #1541 from coqui-ai/comp_emb_fix
Bug fix in compute embedding without eval partition
commit 379ccd7ba6b7e7b550e7d6acf55760c6d0623ba8
Author: WeberJulian <julian.weber@hotmail.fr>
Date: Wed Apr 27 10:42:26 2022 +0200
returns y_mask in VITS inference (#1540)
* returns y_mask
* make style
Mozilla TTS Vocoders (Experimental)
Here there are vocoder model implementations which can be combined with the other TTS models.
Currently, following models are implemented:
- Melgan
- MultiBand-Melgan
- ParallelWaveGAN
- GAN-TTS (Discriminator Only)
It is also very easy to adapt different vocoder models as we provide a flexible and modular (but not too modular) framework.
Training a model
You can see here an example (Soon)Colab Notebook training MelGAN with LJSpeech dataset.
In order to train a new model, you need to gather all wav files into a folder and give this folder to data_path in '''config.json'''
You need to define other relevant parameters in your config.json and then start traning with the following command.
CUDA_VISIBLE_DEVICES='0' python tts/bin/train_vocoder.py --config_path path/to/config.json
Example config files can be found under tts/vocoder/configs/ folder.
You can continue a previous training run by the following command.
CUDA_VISIBLE_DEVICES='0' python tts/bin/train_vocoder.py --continue_path path/to/your/model/folder
You can fine-tune a pre-trained model by the following command.
CUDA_VISIBLE_DEVICES='0' python tts/bin/train_vocoder.py --restore_path path/to/your/model.pth
Restoring a model starts a new training in a different folder. It only restores model weights with the given checkpoint file. However, continuing a training starts from the same directory where the previous training run left off.
You can also follow your training runs on Tensorboard as you do with our TTS models.
Acknowledgement
Thanks to @kan-bayashi for his repository being the start point of our work.