English | 中文
Features
DEMO VIDEO
Quick Start
1. Install Requirements
Follow the original repo to test if you got all environment ready. **Python 3.7 or higher ** is needed to run the toolbox.
- Install PyTorch.
If you get an
ERROR: Could not find a version that satisfies the requirement torch==1.9.0+cu102 (from versions: 0.1.2, 0.1.2.post1, 0.1.2.post2 )This error is probably due to a low version of python, try using 3.9 and it will install successfully
- Install ffmpeg.
- Run
pip install -r requirements.txtto install the remaining necessary packages. - Install webrtcvad
pip install webrtcvad-wheels(If you need)
Note that we are using the pretrained encoder/vocoder but synthesizer, since the original model is incompatible with the Chinese sympols. It means the demo_cli is not working at this moment.
2. Prepare your models
You can either train your models or use existing ones:
2.1 Train encoder with your dataset (Optional)
-
Preprocess with the audios and the mel spectrograms:
python encoder_preprocess.pyAllowing parameter--dataset {dataset}to support the datasets you want to preprocess. Only the train set of these datasets will be used. Possible names: librispeech_other, voxceleb1, voxceleb2. Use comma to sperate multiple datasets. -
Train the encoder:
python encoder_train.py my_run/SV2TTS/encoder
For training, the encoder uses visdom. You can disable it with
--no_visdom, but it's nice to have. Run "visdom" in a separate CLI/process to start your visdom server.
2.2 Train synthesizer with your dataset
-
Download dataset and unzip: make sure you can access all .wav in folder
-
Preprocess with the audios and the mel spectrograms:
python pre.pyAllowing parameter--dataset {dataset}to support aidatatang_200zh, magicdata, aishell3, data_aishell, etc.If this parameter is not passed, the default dataset will be aidatatang_200zh. -
Train the synthesizer:
python synthesizer_train.py mandarin/SV2TTS/synthesizer -
Go to next step when you see attention line show and loss meet your need in training folder synthesizer/saved_models/.
2.3 Use pretrained model of synthesizer
Thanks to the community, some models will be shared:
| author | Download link | Preview Video | Info |
|---|---|---|---|
| @author | https://pan.baidu.com/s/1iONvRxmkI-t1nHqxKytY3g Baidu 4j5d | 75k steps trained by multiple datasets | |
| @author | https://pan.baidu.com/s/1fMh9IlgKJlL2PIiRTYDUvw Baidu code：om7f | 25k steps trained by multiple datasets, only works under version 0.0.1 | |
| @FawenYo | https://drive.google.com/file/d/1H-YGOUHpmqKxJ9FRc6vAjPuqQki24UbC/view?usp=sharing https://u.teknik.io/AYxWf.pt | input output | 200k steps with local accent of Taiwan, only works under version 0.0.1 |
| @miven | https://pan.baidu.com/s/1PI-hM3sn5wbeChRryX-RCQ code：2021 | https://www.bilibili.com/video/BV1uh411B7AD/ | only works under version 0.0.1 |
2.4 Train vocoder (Optional)
note: vocoder has little difference in effect, so you may not need to train a new one.
- Preprocess the data:
python vocoder_preprocess.py-m
replace with your dataset root，replace with directory of your best trained models of sythensizer, e.g. sythensizer\saved_mode\xxx
-
Train the wavernn vocoder:
python vocoder_train.py mandarin -
Train the hifigan vocoder
python vocoder_train.py mandarinhifigan
3. Launch
3.1 Using the web server
You can then try to run:python web.py and open it in browser, default as http://localhost:8080
3.2 Using the Toolbox
You can then try the toolbox: python demo_toolbox.py -d
Reference
This repository is forked from Real-Time-Voice-Cloning which only support English.
| URL | Designation | Title | Implementation source |
|---|---|---|---|
| 1803.09017 | GlobalStyleToken (synthesizer) | Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis | This repo |
| 2010.05646 | HiFi-GAN (vocoder) | Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis | This repo |
| 1806.04558 | SV2TTS | Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis | This repo |
| 1802.08435 | WaveRNN (vocoder) | Efficient Neural Audio Synthesis | fatchord/WaveRNN |
| 1703.10135 | Tacotron (synthesizer) | Tacotron: Towards End-to-End Speech Synthesis | fatchord/WaveRNN |
| 1710.10467 | GE2E (encoder) | Generalized End-To-End Loss for Speaker Verification | This repo |
F Q&A
1.Where can I download the dataset?
| Dataset | Original Source | Alternative Sources |
|---|---|---|
| aidatatang_200zh | OpenSLR | Google Drive |
| magicdata | OpenSLR | Google Drive (Dev set) |
| aishell3 | OpenSLR | Google Drive |
| data_aishell | OpenSLR |
After unzip aidatatang_200zh, you need to unzip all the files under
aidatatang_200zh\corpus\train
2.What is
?
If the dataset path is D:\data\aidatatang_200zh,then
isD:\data
3.Not enough VRAM
Train the synthesizer：adjust the batch_size in synthesizer/hparams.py
//Before
tts_schedule = [(2, 1e-3, 20_000, 12), # Progressive training schedule
(2, 5e-4, 40_000, 12), # (r, lr, step, batch_size)
(2, 2e-4, 80_000, 12), #
(2, 1e-4, 160_000, 12), # r = reduction factor (# of mel frames
(2, 3e-5, 320_000, 12), # synthesized for each decoder iteration)
(2, 1e-5, 640_000, 12)], # lr = learning rate
//After
tts_schedule = [(2, 1e-3, 20_000, 8), # Progressive training schedule
(2, 5e-4, 40_000, 8), # (r, lr, step, batch_size)
(2, 2e-4, 80_000, 8), #
(2, 1e-4, 160_000, 8), # r = reduction factor (# of mel frames
(2, 3e-5, 320_000, 8), # synthesized for each decoder iteration)
(2, 1e-5, 640_000, 8)], # lr = learning rate
Train Vocoder-Preprocess the data：adjust the batch_size in synthesizer/hparams.py
//Before
### Data Preprocessing
max_mel_frames = 900,
rescale = True,
rescaling_max = 0.9,
synthesis_batch_size = 16, # For vocoder preprocessing and inference.
//After
### Data Preprocessing
max_mel_frames = 900,
rescale = True,
rescaling_max = 0.9,
synthesis_batch_size = 8, # For vocoder preprocessing and inference.
Train Vocoder-Train the vocoder：adjust the batch_size in vocoder/wavernn/hparams.py
//Before
# Training
voc_batch_size = 100
voc_lr = 1e-4
voc_gen_at_checkpoint = 5
voc_pad = 2
//After
# Training
voc_batch_size = 6
voc_lr = 1e-4
voc_gen_at_checkpoint = 5
voc_pad =2
4.If it happens RuntimeError: Error(s) in loading state_dict for Tacotron: size mismatch for encoder.embedding.weight: copying a param with shape torch.Size([70, 512]) from checkpoint, the shape in current model is torch.Size([75, 512]).
Please refer to issue #37
5. How to improve CPU and GPU occupancy rate?
Adjust the batch_size as appropriate to improve
6. What if it happens the page file is too small to complete the operation
Please refer to this video and change the virtual memory to 100G (102400), for example : When the file is placed in the D disk, the virtual memory of the D disk is changed.
7. When should I stop during training?
FYI, my attention came after 18k steps and loss became lower than 0.4 after 50k steps. 
![FileNotFoundError: [Errno 2] No such file or directory: 'encoder\\saved_models\\pretrained.pt'](https://avatars.githubusercontent.com/u/62303408?v=4)
19 Jun 30, 2022
6 Nov 8, 2022
575 Dec 31, 2022
2 Jun 19, 2022
15.3k Dec 30, 2022
3 Oct 15, 2021
16 Dec 7, 2022
14 Dec 9, 2022
2.2k Jan 9, 2023
22 Nov 13, 2022
11 Nov 17, 2022
3.2k Dec 31, 2022
1k Dec 30, 2022
5 Dec 28, 2021
1 Dec 20, 2021
29 Oct 16, 2022
873 Dec 15, 2022