Clone a voice in 5 seconds to generate arbitrary speech in real-time
Corentin Jemine 911679d0c2 Now only listing open source TTS alternatives | před 6 měsíci | |
---|---|---|
encoder | před 3 roky | |
samples | před 4 roky | |
synthesizer | před 3 roky | |
toolbox | před 3 roky | |
utils | před 2 roky | |
vocoder | před 3 roky | |
.gitattributes | před 5 roky | |
.gitignore | před 5 roky | |
LICENSE.md | před 3 roky | |
README.md | před 6 měsíci | |
demo_cli.py | před 3 roky | |
demo_toolbox.py | před 3 roky | |
encoder_preprocess.py | před 3 roky | |
encoder_train.py | před 3 roky | |
requirements.txt | před 3 roky | |
synthesizer_preprocess_audio.py | před 3 roky | |
synthesizer_preprocess_embeds.py | před 3 roky | |
synthesizer_train.py | před 3 roky | |
vocoder_preprocess.py | před 3 roky | |
vocoder_train.py | před 3 roky |
This repository is an implementation of Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis (SV2TTS) with a vocoder that works in real-time. This was my master's thesis.
SV2TTS is a deep learning framework in three stages. In the first stage, one creates a digital representation of a voice from a few seconds of audio. In the second and third stages, this representation is used as reference to generate speech given arbitrary text.
Video demonstration (click the picture):
URL | Designation | Title | Implementation source |
---|---|---|---|
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 |
Like everything else in Deep Learning, this repo has quickly gotten old. Many SaaS apps (often paying) will give you a better audio quality than this repository will. If you wish for an open-source solution with a high voice quality:
venv
, but this is optional.pip install -r requirements.txt
Pretrained models are now downloaded automatically. If this doesn't work for you, you can manually download them here.
Before you download any dataset, you can begin by testing your configuration with:
python demo_cli.py
If all tests pass, you're good to go.
For playing with the toolbox alone, I only recommend downloading LibriSpeech/train-clean-100
. Extract the contents as <datasets_root>/LibriSpeech/train-clean-100
where <datasets_root>
is a directory of your choosing. Other datasets are supported in the toolbox, see here. You're free not to download any dataset, but then you will need your own data as audio files or you will have to record it with the toolbox.
You can then try the toolbox:
python demo_toolbox.py -d <datasets_root>
or
python demo_toolbox.py
depending on whether you downloaded any datasets. If you are running an X-server or if you have the error Aborted (core dumped)
, see this issue.