Spaces:
Sleeping
A newer version of the Gradio SDK is available:
4.42.0
vits_hifitts Recipe
In this recipe, we will show how to train vits_hifitts using Amphion's infrastructure. vits_hifitts is an end-to-end TTS architecture that utilizes conditional variational autoencoder with adversarial learning.
There are four stages in total:
- Data preparation
- Features extraction
- Training
- Inference
NOTE: You need to run every command of this recipe in the
Amphion
root path:
cd Amphion
1. Data Preparation
Dataset Download
You can use the commonly used TTS dataset to train TTS model, e.g., LJSpeech, VCTK, LibriTTS, etc. We strongly recommend you use LJSpeech to train TTS model for the first time. How to download dataset is detailed here.
Configuration
After downloading the dataset, you can set the dataset paths in exp_config.json
. Note that you can change the dataset
list to use your preferred datasets.
"dataset": [
"LJSpeech",
],
"dataset_path": {
// TODO: Fill in your dataset path
"LJSpeech": "[LJSpeech dataset path]",
},
2. Features Extraction
Configuration
Specify the processed_dir
and the log_dir
and for saving the processed data and the checkpoints in exp_config.json
:
// TODO: Fill in the output log path. The default value is "Amphion/ckpts/tts"
"log_dir": "ckpts/tts",
"preprocess": {
// TODO: Fill in the output data path. The default value is "Amphion/data"
"processed_dir": "data",
...
},
Run
Run the run.sh
as the preproces stage (set --stage 1
):
sh egs/tts/vits_hifitts/run.sh --stage 1
NOTE: The
CUDA_VISIBLE_DEVICES
is set as"0"
in default. You can change it when runningrun.sh
by specifying such as--gpu "1"
.
3. Training
Configuration
We provide the default hyparameters in the exp_config.json
. They can work on single NVIDIA-24g GPU. You can adjust them based on your GPU machines.
"train": {
"batch_size": 16,
}
Run
Run the run.sh
as the training stage (set --stage 2
). Specify a experimental name to run the following command. The tensorboard logs and checkpoints will be saved in Amphion/ckpts/tts/[YourExptName]
.
sh egs/tts/vits_hifitts/run.sh --stage 2 --name [YourExptName]
NOTE: The
CUDA_VISIBLE_DEVICES
is set as"0"
in default. You can change it when runningrun.sh
by specifying such as--gpu "0,1,2,3"
.
4. Inference
Configuration
For inference, you need to specify the following configurations when running run.sh
:
Parameters | Description | Example |
---|---|---|
--infer_expt_dir |
The experimental directory which contains checkpoint |
Amphion/ckpts/tts/[YourExptName] |
--infer_output_dir |
The output directory to save inferred audios. | Amphion/ckpts/tts/[YourExptName]/result |
--infer_mode |
The inference mode, e.g., "single ", "batch ". |
"single " to generate a clip of speech, "batch " to generate a batch of speech at a time. |
--infer_dataset |
The dataset used for inference. | For LJSpeech dataset, the inference dataset would be LJSpeech . |
--infer_testing_set |
The subset of the inference dataset used for inference, e.g., train, test, golden_test | For LJSpeech dataset, the testing set would be "test " split from LJSpeech at the feature extraction, or "golden_test " cherry-picked from test set as template testing set. |
--infer_text |
The text to be synthesized. | "This is a clip of generated speech with the given text from a TTS model. " |
Run
For example, if you want to generate speech of all testing set split from LJSpeech, just run:
sh egs/tts/vits_hifitts/run.sh --stage 3 --gpu "0" \
--infer_expt_dir Amphion/ckpts/tts/[YourExptName] \
--infer_output_dir Amphion/ckpts/tts/[YourExptName]/result \
--infer_mode "batch" \
--infer_dataset "LJSpeech" \
--infer_testing_set "test"
Or, if you want to generate a single clip of speech from a given text, just run:
sh egs/tts/vits_hifitts/run.sh --stage 3 --gpu "0" \
--infer_expt_dir Amphion/ckpts/tts/[YourExptName] \
--infer_output_dir Amphion/ckpts/tts/[YourExptName]/result \
--infer_mode "single" \
--infer_text "This is a clip of generated speech with the given text from a TTS model."
We will release a pre-trained vits_hifitts model trained on LJSpeech. So you can download the pre-trained model and generate speech following the above inference instruction.
@inproceedings{kim2021conditional,
title={Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech},
author={Kim, Jaehyeon and Kong, Jungil and Son, Juhee},
booktitle={International Conference on Machine Learning},
pages={5530--5540},
year={2021},
}