Metadata-Version: 2.4
Name: tts_webui_extension.seamless_m4t
Version: 0.0.7
Summary: SeamlessM4T is a multilingual and multimodal translation model supporting text and speech
Home-page: https://github.com/rsxdalv/tts_webui_extension.seamless_m4t
Author: rsxdalv
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: transformers>=4.30.0
Requires-Dist: torchaudio>=2.0.0
Dynamic: author
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license-file
Dynamic: requires-dist
Dynamic: summary

# Extension adapter for SeamlessM4T

License - the source code within this repository is licensed under the MIT license.

This extension provides a multilingual and multimodal translation model that supports text and speech translation across many languages.

## Features

- Text-to-Speech translation: Translate text from one language to speech in another language
- Audio-to-Speech translation: Translate speech from one language to speech in another language
- Support for over 100 languages for text input
- Support for over 35 languages for speech output
- High-quality speech synthesis

## Usage

### Text to Speech Translation
1. Enter your text in the input field
2. Select the source language of your text
3. Select the target language for the speech output
4. Click "Translate Text to Speech" to generate the translated speech

### Audio to Speech Translation
1. Upload an audio file containing speech
2. Select the target language for the speech output
3. Click "Translate Audio to Speech" to generate the translated speech

This extension uses the [SeamlessM4Tv2Model](https://huggingface.co/facebook/seamless-m4t-v2-large) model from HuggingFace.
