Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/smoke-trees/voice-synthesis
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. SV2TTS is a three-stage deep learning framework that allows to create a numerical representation of a voice from a few seconds of audio, and to use it to condition a text-to-speech model trained to generalize to new voices.
https://github.com/smoke-trees/voice-synthesis
keras pytorch-implementation speech-to-text sv2tts tensorflow voice-cloning voice-synthesis
Last synced: 2 months ago
JSON representation
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. SV2TTS is a three-stage deep learning framework that allows to create a numerical representation of a voice from a few seconds of audio, and to use it to condition a text-to-speech model trained to generalize to new voices.
- Host: GitHub
- URL: https://github.com/smoke-trees/voice-synthesis
- Owner: smoke-trees
- Created: 2020-05-03T20:59:45.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2020-09-25T19:02:05.000Z (over 4 years ago)
- Last Synced: 2023-11-07T17:36:30.380Z (about 1 year ago)
- Topics: keras, pytorch-implementation, speech-to-text, sv2tts, tensorflow, voice-cloning, voice-synthesis
- Language: Python
- Homepage:
- Size: 3.12 MB
- Stars: 153
- Watchers: 4
- Forks: 43
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
Voice Cloning and Text to Speech Synthesis
A Standalone service for cloning your own voice and synthesize any text in English in your own voice.
Read more about the procedure we followed and the findings [here](src/README.md)
---
## Functionalities
- [X] Clone voices after feeding samples to it
- [X] Synthesized voice on custom texts
- [X] Speech-to-text facility for input using microphones
- [X] RestAPI with a testing UI for testing the model
## Instructions to run the trained models
If you want to try and test out the samples trained and how the model is performing on custom text you can follow these instructions.
* Pre-requisites:
- For Windows
- python (3.6 or 3.7 works best)
- virtualenv
> If you dont have virtualenv check it out here to [install](https://programwithus.com/learn-to-code/Pip-and-virtualenv-on-Windows/)
- Trained embeddings from [here](https://drive.google.com/uc?id=1n1sPXvT34yXFLT47QZA6FIRGrwMeSsZc)
- For linux
- Bash shell for executing the scripts
* Directions to install:
- For windows
- Clone the repo
- Setup Virtualenv
``` cmd
virtualenv env
cd env/scripts
activate
```
- Install all requirements packages
``` cmd
pip install -r requirements.txt
```
- For Linux
- Run the run.sh file to install the project
``` bash
./run.sh
```
After installing all the dependencies and environment prerequisites run the below file to check you are ready and good to go!
``` bash
./test.sh
```
* Directions to execute
- Test through interface
- Start the python flask server
``` python
python app.py
```
- Log on to localhost:5000 to test the model
- Test through the Synthesize function
- Follow the instructions given [here](src/README.md)
- Test using Docker
```bash
docker build -t smoketrees/voice:latest .
docker run smoketrees/voice:latest -p 5000:5000
```
## Instructions to train your own models
If you want to work with the source code and want to train your own models on different dataset and different language medium you can check out the instructions mentioned [here](src/README.md)
For more information about the samples tested and there results you can get all the information from [here](src/README.md)
## Contributors
* [SmokeTrees](https://github.com/smoke-trees)
* [Tanmay Agarwal](https://github.com/Tanmay244)