Metadata-Version: 2.1
Name: speechtoolkit
Version: 0.0.1
Summary: ML for Speech presents SpeechToolkit, a unified, all-in-one toolkit for TTS, ASR, VC, & other models.
Home-page: https://github.com/ml-for-speech/speechtoolkit
Author: ml-for-speech
Description-Content-Type: text/markdown
Requires-Dist: soundfile
Requires-Dist: librosa
Requires-Dist: torch
Requires-Dist: transformers
Requires-Dist: optimum
Provides-Extra: all
Requires-Dist: lvc ; extra == 'all'
Requires-Dist: ns3vc ; extra == 'all'
Requires-Dist: flash-attn ; extra == 'all'
Requires-Dist: openai-whisper ; extra == 'all'
Provides-Extra: asr
Requires-Dist: openai-whisper ; extra == 'asr'
Provides-Extra: dev
Requires-Dist: mkdocs ; extra == 'dev'
Requires-Dist: mkautodoc ; extra == 'dev'
Provides-Extra: fa2
Requires-Dist: flash-attn ; extra == 'fa2'
Provides-Extra: vc
Requires-Dist: lvc ; extra == 'vc'
Requires-Dist: ns3vc ; extra == 'vc'

# SpeechToolkit

**NOTE: This project is still in an early alpha stage and is not ready for production yet.**

ML for Speech presents SpeechToolkit, a unified framework for text-to-speech, voice conversion, automatic speech recognition, audio classification, voice activity detection, and more!

Please note that this toolkit is currently in an early alpha and not all features have been implemented.

If you prefer not to use SpeechToolkit but would like to interact with models individually and separately, please check out the [ML for Speech](https://github.com/ml-for-speech) page.

## Installation & Usage

Documentation is available [online](https://ml-for-speech.github.io/speechtoolkit).
