# ttsmms
Text-to-speech with The Massively Multilingual Speech (MMS) project
This project want to help you for use Text-to-speech model from MMS project in Python.
Support 1,107 Languages! (See support_list.txt)
- VITS: [GitHub](https://github.com/jaywalnut310/vits)
- MMS: Scaling Speech Technology to 1000+ languages: [GitHub](https://github.com/facebookresearch/fairseq/tree/main/examples/mms)
[Google colab](https://colab.research.google.com/github/wannaphong/ttsmms/blob/main/notebook/test.ipynb)
**Don't forget the TTS model in MMS project use CC-BY-NC license.**
## Install
> pip install ttsmms
## Usage
First, you need to download the model by
```python
from ttsmms import download
dir_path = download("eng","./data") # lang_code, dir for save model
```
or download file by yourself
**Linux/Mac**
1. download
> curl https://dl.fbaipublicfiles.com/mms/tts/lang_code.tar.gz --output lang_code.tar.gz
2. extract a tar ball archive.
**Linux/Mac**
> mkdir -p data && tar -xzf lang_code.tar.gz -C data/
and use code in python :D
```python
from ttsmms import TTS
tts=TTS(dir_path) # or "model_dir_path" your path dir that extract a tar ball archive
wav=tts.synthesis("txt")
# output:
# {
# "x":array(wav array),
# "sampling_rate": 16000
# }
tts.synthesis("txt",wav_path="example.wav")
# output: example.wav file
```
Raw data
{
"_id": null,
"home_page": "https://github.com/wannaphong/ttsmms",
"name": "ttsmms",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": "",
"keywords": "tts,NLP",
"author": "Wannaphong",
"author_email": "wannaphong@yahoo.com",
"download_url": "https://files.pythonhosted.org/packages/4d/07/6075aa0b1c4574764e898fea2ee4c125cb4270f6db074617e2cea3586644/ttsmms-0.7.tar.gz",
"platform": null,
"description": "# ttsmms\nText-to-speech with The Massively Multilingual Speech (MMS) project\n\nThis project want to help you for use Text-to-speech model from MMS project in Python.\n\nSupport 1,107 Languages! (See support_list.txt)\n\n- VITS: [GitHub](https://github.com/jaywalnut310/vits)\n- MMS: Scaling Speech Technology to 1000+ languages: [GitHub](https://github.com/facebookresearch/fairseq/tree/main/examples/mms)\n\n[Google colab](https://colab.research.google.com/github/wannaphong/ttsmms/blob/main/notebook/test.ipynb)\n\n**Don't forget the TTS model in MMS project use CC-BY-NC license.**\n\n## Install\n\n> pip install ttsmms\n\n\n## Usage\n\nFirst, you need to download the model by\n\n```python\nfrom ttsmms import download\n\ndir_path = download(\"eng\",\"./data\") # lang_code, dir for save model\n```\n\nor download file by yourself\n\n**Linux/Mac**\n\n1. download\n\n> curl https://dl.fbaipublicfiles.com/mms/tts/lang_code.tar.gz --output lang_code.tar.gz\n\n2. extract a tar ball archive.\n\n**Linux/Mac**\n\n> mkdir -p data && tar -xzf lang_code.tar.gz -C data/\n\nand use code in python :D\n\n```python\nfrom ttsmms import TTS\n\ntts=TTS(dir_path) # or \"model_dir_path\" your path dir that extract a tar ball archive\nwav=tts.synthesis(\"txt\")\n# output:\n# {\n# \"x\":array(wav array),\n# \"sampling_rate\": 16000\n# }\n\ntts.synthesis(\"txt\",wav_path=\"example.wav\")\n# output: example.wav file\n```\n",
"bugtrack_url": null,
"license": "MIT License",
"summary": "Text-to-speech with The Massively Multilingual Speech (MMS) project",
"version": "0.7",
"project_urls": {
"Homepage": "https://github.com/wannaphong/ttsmms",
"Source": "https://github.com/wannaphong/ttsmms"
},
"split_keywords": [
"tts",
"nlp"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "79a9f8879bf9dacd9199d5829e6e1c63938c7dfc752c023744b39810db2d5d8d",
"md5": "3b6bad93c26df41a82c9f953b227e307",
"sha256": "617e4dc07bf3ad2e3e902fdb11ca1f9afbed9ba99abfc1476959d9d880f27c84"
},
"downloads": -1,
"filename": "ttsmms-0.7-py3-none-any.whl",
"has_sig": false,
"md5_digest": "3b6bad93c26df41a82c9f953b227e307",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6",
"size": 29411,
"upload_time": "2023-05-30T14:50:51",
"upload_time_iso_8601": "2023-05-30T14:50:51.936971Z",
"url": "https://files.pythonhosted.org/packages/79/a9/f8879bf9dacd9199d5829e6e1c63938c7dfc752c023744b39810db2d5d8d/ttsmms-0.7-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "4d076075aa0b1c4574764e898fea2ee4c125cb4270f6db074617e2cea3586644",
"md5": "29d950e1179db16a6a198b7add8db267",
"sha256": "c9d1ca9d239551a39bc2194c208d999ffee05242e90da09af7517b1ff9fd7575"
},
"downloads": -1,
"filename": "ttsmms-0.7.tar.gz",
"has_sig": false,
"md5_digest": "29d950e1179db16a6a198b7add8db267",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 26789,
"upload_time": "2023-05-30T14:50:53",
"upload_time_iso_8601": "2023-05-30T14:50:53.558147Z",
"url": "https://files.pythonhosted.org/packages/4d/07/6075aa0b1c4574764e898fea2ee4c125cb4270f6db074617e2cea3586644/ttsmms-0.7.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-05-30 14:50:53",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "wannaphong",
"github_project": "ttsmms",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "ttsmms"
}