Clone a voice in 5 seconds to generate arbitrary speech in real-time

English | 中文

Features

🌍 Chinese supported mandarin and tested with multiple datasets: aidatatang_200zh, magicdata, aishell3, data_aishell, and etc.

🤩 PyTorch worked for pytorch, tested in version of 1.9.0(latest in August 2021), with GPU Tesla T4 and GTX 2060

🌍 Windows + Linux run in both Windows OS and linux OS (even in M1 MACOS)

🤩 Easy & Awesome effect with only newly-trained synthesizer, by reusing the pretrained encoder/vocoder

🌍 Webserver Ready to serve your result with remote calling

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.

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.txt to 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.py <datasets_root> Allowing 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 <datasets_root>/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.py <datasets_root> Allowing 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 <datasets_root>/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:

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 <datasets_root> -m <synthesizer_model_path>

<datasets_root> replace with your dataset root，<synthesizer_model_path>replace with directory of your best trained models of sythensizer, e.g. sythensizer\saved_mode\xxx

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 <datasets_root>

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?

After unzip aidatatang_200zh, you need to unzip all the files under aidatatang_200zh\corpus\train

2.What is<datasets_root>?

If the dataset path is D:\data\aidatatang_200zh,then <datasets_root> 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.

from Hacker News https://ift.tt/3zp0Wm8