zhangshuai/MeloTTS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add docker

Browse Source
This commit is contained in:
qinzy
2024-02-27 18:04:21 -07:00
parent 5bcbf94746
commit f7380ed7ab
5 changed files with 289 additions and 212 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Dockerfile
View File

@@ -10,4 +10,4 @@ RUN pip install -e .
RUN python -m unidic download RUN python -m unidic download
RUN python melo/init_downloads.py RUN python melo/init_downloads.py
CMD ["python", "./melo/app.py", "--port", "8800"] CMD ["python", "./melo/app.py", "--host", "0.0.0.0", "--port", "8888"]

215
README.md
View File

@@ -23,216 +23,9 @@ Some other features include:
- The Chinese speaker supports `mixed Chinese and English`. - The Chinese speaker supports `mixed Chinese and English`.
- Fast enough for `CPU real-time inference`. - Fast enough for `CPU real-time inference`.
## Install on Linux or macOS
**Installation:**
```bash
pip install git+https://github.com/myshell-ai/MeloTTS.git
python -m unidic download
```
**Manual installation:**
```bash
git clone https://github.com/myshell-ai/MeloTTS.git
cd MeloTTS
pip install -e .
python -m unidic download
```
We welcome the open-source community to make this repo `Windows` compatible. If you find this repo useful, please consider contributing to the repo.
## Usage ## Usage
- [Use without Installation](docs/quick_use.md)
An unofficial [live demo](https://huggingface.co/spaces/mrfakename/MeloTTS) is hosted on Hugging Face Spaces. - [Install and Use Locally](docs/install.md)
### WebUI
The WebUI supports muliple languages and voices. First, follow the installation steps. Then, simply run:
```bash
melo-ui
# Or: python melo/app.py
```
### CLI
You may use the MeloTTS CLI to interact with MeloTTS. The CLI may be invoked using either `melotts` or `melo`. Here are some examples:
**Read English text:**
```bash
melo "Text to read" output.wav
```
**Specify a language:**
```bash
melo "Text to read" output.wav --language EN
```
**Specify a speaker:**
```bash
melo "Text to read" output.wav --language EN --speaker EN-US
melo "Text to read" output.wav --language EN --speaker EN-AU
```
The available speakers are: `EN-Default`, `EN-US`, `EN-BR`, `EN-INDIA` `EN-AU`.
**Specify a speed:**
```bash
melo "Text to read" output.wav --language EN --speaker EN-US --speed 1.5
melo "Text to read" output.wav --speed 1.5
```
**Use a different language:**
```bash
melo "text-to-speech 领域近年来发展迅速" zh.wav -l ZH
```
**Load from a file:**
```bash
melo file.txt out.wav --file
```
The full API documentation may be found using:
```bash
melo --help
```
### Python API
#### English with Multiple Accents
```python
from melo.api import TTS
# Speed is adjustable
speed = 1.0
# CPU is sufficient for real-time inference.
# You can set it manually to 'cpu' or 'cuda' or 'cuda:0' or 'mps'
device = 'auto' # Will automatically use GPU if available
# English
text = "Did you ever hear a folk tale about a giant turtle?"
model = TTS(language='EN', device=device)
speaker_ids = model.hps.data.spk2id
# American accent
output_path = 'en-us.wav'
model.tts_to_file(text, speaker_ids['EN-US'], output_path, speed=speed)
# British accent
output_path = 'en-br.wav'
model.tts_to_file(text, speaker_ids['EN-BR'], output_path, speed=speed)
# Indian accent
output_path = 'en-india.wav'
model.tts_to_file(text, speaker_ids['EN_INDIA'], output_path, speed=speed)
# Australian accent
output_path = 'en-au.wav'
model.tts_to_file(text, speaker_ids['EN-AU'], output_path, speed=speed)
# Default accent
output_path = 'en-default.wav'
model.tts_to_file(text, speaker_ids['EN-Default'], output_path, speed=speed)
```
### Spanish
```python
from melo.api import TTS
# Speed is adjustable
speed = 1.0
# CPU is sufficient for real-time inference.
# You can also change to cuda:0
device = 'cpu'
text = "El resplandor del sol acaricia las olas, pintando el cielo con una paleta deslumbrante."
model = TTS(language='ES', device=device)
speaker_ids = model.hps.data.spk2id
output_path = 'es.wav'
model.tts_to_file(text, speaker_ids['ES'], output_path, speed=speed)
```
#### French
```python
from melo.api import TTS
# Speed is adjustable
speed = 1.0
device = 'cpu' # or cuda:0
text = "La lueur dorée du soleil caresse les vagues, peignant le ciel d'une palette éblouissante."
model = TTS(language='FR', device=device)
speaker_ids = model.hps.data.spk2id
output_path = 'fr.wav'
model.tts_to_file(text, speaker_ids['FR'], output_path, speed=speed)
```
#### Chinese
```python
from melo.api import TTS
# Speed is adjustable
speed = 1.0
device = 'cpu' # or cuda:0
text = "我最近在学习machine learning，希望能够在未来的artificial intelligence领域有所建树。"
model = TTS(language='ZH', device=device)
speaker_ids = model.hps.data.spk2id
output_path = 'zh.wav'
model.tts_to_file(text, speaker_ids['ZH'], output_path, speed=speed)
```
#### Japanese
```python
from melo.api import TTS
# Speed is adjustable
speed = 1.0
device = 'cpu' # or cuda:0
text = "彼は毎朝ジョギングをして体を健康に保っています。"
model = TTS(language='JP', device=device)
speaker_ids = model.hps.data.spk2id
output_path = 'jp.wav'
model.tts_to_file(text, speaker_ids['JP'], output_path, speed=speed)
```
#### Korean
```python
from melo.api import TTS
# Speed is adjustable
speed = 1.0
device = 'cpu' # or cuda:0
text = "안녕하세요! 오늘은 날씨가 정말 좋네요."
model = TTS(language='KR', device=device)
speaker_ids = model.hps.data.spk2id
output_path = 'kr.wav'
model.tts_to_file(text, speaker_ids['KR'], output_path, speed=speed)
```
## License ## License
@@ -240,4 +33,6 @@ This library is under MIT License, which means it is free for both commercial an
## Acknowledgements ## Acknowledgements
This implementation is based on several excellent projects, [TTS](https://github.com/coqui-ai/TTS), [VITS](https://github.com/jaywalnut310/vits), [VITS2](https://github.com/daniilrobnikov/vits2) and [Bert-VITS2](https://github.com/fishaudio/Bert-VITS2). We appreciate their awesome work! This implementation is based on [TTS](https://github.com/coqui-ai/TTS), [VITS](https://github.com/jaywalnut310/vits), [VITS2](https://github.com/daniilrobnikov/vits2) and [Bert-VITS2](https://github.com/fishaudio/Bert-VITS2). We appreciate their awesome work.
Many thanks to [@fakerybakery](https://github.com/fakerybakery) for adding the Web UI and CLI part.

234
docs/install.md Normal file
View File

@@ -0,0 +1,234 @@
## Install and Use Locally
### Table of Content
- [Linux Install](#linux-install)
- [Windows and macOS](#windows-and-macos-install)
- [Usage](#usage)
- [Web UI](#webui)
- [CLI](#cli)
- [Python API](#python-api)
### Linux Install
Use pip to install from github repo.
```bash
pip install git+https://github.com/myshell-ai/MeloTTS.git
python -m unidic download
```
Alternatively, you may run manual installation:
```bash
git clone https://github.com/myshell-ai/MeloTTS.git
cd MeloTTS
pip install -e .
python -m unidic download
```
### Windows and macOS Install
To avoid compatibility issues, for Windows and macOS users, we suggest to run via Docker. Ensure that [you have Docker installed](https://docs.docker.com/engine/install/).
**Build Docker**
This could take a few minutes.
```bash
git clone https://github.com/myshell-ai/MeloTTS.git
cd MeloTTS
docker build -t melotts .
```
**Run Docker**
```bash
docker run -it -p 8888:8888 melotts
```
Then open [http://localhost:8888](http://localhost:8888) in your browser to use the app.
## Usage
### WebUI
The WebUI supports muliple languages and voices. First, follow the installation steps. Then, simply run:
```bash
melo-ui
# Or: python melo/app.py
```
### CLI
You may use the MeloTTS CLI to interact with MeloTTS. The CLI may be invoked using either `melotts` or `melo`. Here are some examples:
**Read English text:**
```bash
melo "Text to read" output.wav
```
**Specify a language:**
```bash
melo "Text to read" output.wav --language EN
```
**Specify a speaker:**
```bash
melo "Text to read" output.wav --language EN --speaker EN-US
melo "Text to read" output.wav --language EN --speaker EN-AU
```
The available speakers are: `EN-Default`, `EN-US`, `EN-BR`, `EN_INDIA` `EN-AU`.
**Specify a speed:**
```bash
melo "Text to read" output.wav --language EN --speaker EN-US --speed 1.5
melo "Text to read" output.wav --speed 1.5
```
**Use a different language:**
```bash
melo "text-to-speech 领域近年来发展迅速" zh.wav -l ZH
```
**Load from a file:**
```bash
melo file.txt out.wav --file
```
The full API documentation may be found using:
```bash
melo --help
```
### Python API
#### English with Multiple Accents
```python
from melo.api import TTS
# Speed is adjustable
speed = 1.0
# CPU is sufficient for real-time inference.
# You can set it manually to 'cpu' or 'cuda' or 'cuda:0' or 'mps'
device = 'auto' # Will automatically use GPU if available
# English
text = "Did you ever hear a folk tale about a giant turtle?"
model = TTS(language='EN', device=device)
speaker_ids = model.hps.data.spk2id
# American accent
output_path = 'en-us.wav'
model.tts_to_file(text, speaker_ids['EN-US'], output_path, speed=speed)
# British accent
output_path = 'en-br.wav'
model.tts_to_file(text, speaker_ids['EN-BR'], output_path, speed=speed)
# Indian accent
output_path = 'en-india.wav'
model.tts_to_file(text, speaker_ids['EN_INDIA'], output_path, speed=speed)
# Australian accent
output_path = 'en-au.wav'
model.tts_to_file(text, speaker_ids['EN-AU'], output_path, speed=speed)
# Default accent
output_path = 'en-default.wav'
model.tts_to_file(text, speaker_ids['EN-Default'], output_path, speed=speed)
```
### Spanish
```python
from melo.api import TTS
# Speed is adjustable
speed = 1.0
# CPU is sufficient for real-time inference.
# You can also change to cuda:0
device = 'cpu'
text = "El resplandor del sol acaricia las olas, pintando el cielo con una paleta deslumbrante."
model = TTS(language='ES', device=device)
speaker_ids = model.hps.data.spk2id
output_path = 'es.wav'
model.tts_to_file(text, speaker_ids['ES'], output_path, speed=speed)
```
#### French
```python
from melo.api import TTS
# Speed is adjustable
speed = 1.0
device = 'cpu' # or cuda:0
text = "La lueur dorée du soleil caresse les vagues, peignant le ciel d'une palette éblouissante."
model = TTS(language='FR', device=device)
speaker_ids = model.hps.data.spk2id
output_path = 'fr.wav'
model.tts_to_file(text, speaker_ids['FR'], output_path, speed=speed)
```
#### Chinese
```python
from melo.api import TTS
# Speed is adjustable
speed = 1.0
device = 'cpu' # or cuda:0
text = "我最近在学习machine learning，希望能够在未来的artificial intelligence领域有所建树。"
model = TTS(language='ZH', device=device)
speaker_ids = model.hps.data.spk2id
output_path = 'zh.wav'
model.tts_to_file(text, speaker_ids['ZH'], output_path, speed=speed)
```
#### Japanese
```python
from melo.api import TTS
# Speed is adjustable
speed = 1.0
device = 'cpu' # or cuda:0
text = "彼は毎朝ジョギングをして体を健康に保っています。"
model = TTS(language='JP', device=device)
speaker_ids = model.hps.data.spk2id
output_path = 'jp.wav'
model.tts_to_file(text, speaker_ids['JP'], output_path, speed=speed)
```
#### Korean
```python
from melo.api import TTS
# Speed is adjustable
speed = 1.0
device = 'cpu' # or cuda:0
text = "안녕하세요! 오늘은 날씨가 정말 좋네요."
model = TTS(language='KR', device=device)
speaker_ids = model.hps.data.spk2id
output_path = 'kr.wav'
model.tts_to_file(text, speaker_ids['KR'], output_path, speed=speed)
```

48
docs/quick_use.md Normal file
View File

@@ -0,0 +1,48 @@
## Use MeloTTS without Installation
**Quick Demo**
An unofficial [live demo](https://huggingface.co/spaces/mrfakename/MeloTTS) is hosted on Hugging Face Spaces.
**Use on MyShell**
There are hundreds of TTS models on MyShell, much more than MeloTTS. For example:
English
- [gentle British male voice](https://app.myshell.ai/widget/nIfamm)
- [cheerful young female voice](https://app.myshell.ai/widget/AjIjqy)
- [sultry and robust male voice](https://app.myshell.ai/widget/zQJJN3)
Spanish
- [voz femenina adorable](https://app.myshell.ai/widget/buIZBf)
- [voz masculina joven](https://app.myshell.ai/widget/rayuiy)
- [voz de niña inmadura](https://app.myshell.ai/widget/mYFV3e)
French
- [voix adorable de fille](https://app.myshell.ai/widget/3IfEfy)
- [voix douce masculine](https://app.myshell.ai/widget/IRR3M3)
- [voix douce féminine](https://app.myshell.ai/widget/NRbaUj)
German
- [sanfte Männerstimme](https://app.myshell.ai/widget/JFnAn2)
- [sanfte Frauenstimme](https://app.myshell.ai/widget/MrU7Nb)
- [unreife Mädchenstimme](https://app.myshell.ai/widget/UFbYBj)
Portuguese
- [voz feminina nítida](https://app.myshell.ai/widget/VzMb6j)
- [voz de menino imaturo](https://app.myshell.ai/widget/nAzeei)
- [voz masculina sóbria](https://app.myshell.ai/widget/JZRNJz)
Arabic
- [صوت امرأة ناضجة" في اللغة](https://app.myshell.ai/widget/zqMruu)
- [صوت رجل ناضج" في اللغة العربية](https://app.myshell.ai/widget/iqMbQr)
Russian
- [зрелый женский голос](https://app.myshell.ai/widget/6byMZ3)
- [зрелый мужской голос](https://app.myshell.ai/widget/NB7jmm)
Chinese
- [甜美女声](https://app.myshell.ai/widget/ymeUjm)
- [青年男声](https://app.myshell.ai/widget/NZnERb)
More can be found at the widget center of [MyShell.ai](https://app.myshell.ai/robot-workshop).

2
melo/app.py
View File

@@ -41,7 +41,7 @@ def load_speakers(language, text):
with gr.Blocks() as demo: with gr.Blocks() as demo:
gr.Markdown('# MeloTTS WebUI\n\nA WebUI for MeloTTS.') gr.Markdown('# MeloTTS WebUI\n\nA WebUI for MeloTTS.')
with gr.Group(): with gr.Group():
speaker = gr.Dropdown(speaker_ids.keys(), interactive=True, value='EN-Default', label='Speaker') speaker = gr.Dropdown(speaker_ids.keys(), interactive=True, value='EN-US', label='Speaker')
language = gr.Radio(['EN', 'ES', 'FR', 'ZH', 'JP', 'KR'], label='Language', value='EN') language = gr.Radio(['EN', 'ES', 'FR', 'ZH', 'JP', 'KR'], label='Language', value='EN')
speed = gr.Slider(label='Speed', minimum=0.1, maximum=10.0, value=1.0, interactive=True, step=0.1) speed = gr.Slider(label='Speed', minimum=0.1, maximum=10.0, value=1.0, interactive=True, step=0.1)
text = gr.Textbox(label="Text to speak", value=default_text_dict['EN']) text = gr.Textbox(label="Text to speak", value=default_text_dict['EN'])