Metadata-Version: 2.1
Name: fast_tts
Version: 0.0.3
Home-page: https://github.com/mathieutrudeau/Fast-TTS
Author: Mathieu Trudeau
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: tbb
Requires-Dist: mpmath
Requires-Dist: MarkupSafe
Requires-Dist: intel-openmp
Requires-Dist: typing-extensions
Requires-Dist: sympy
Requires-Dist: networkx
Requires-Dist: mkl
Requires-Dist: jinja2
Requires-Dist: fsspec
Requires-Dist: filelock
Requires-Dist: torch
Requires-Dist: pillow
Requires-Dist: numpy
Requires-Dist: torchvision
Requires-Dist: torchaudio
Requires-Dist: einops
Requires-Dist: transformers<=4.19.0
Requires-Dist: librosa
Requires-Dist: inflect
Requires-Dist: unidecode
Requires-Dist: psutil
Requires-Dist: av<=11.0.0
Requires-Dist: faiss-cpu
Requires-Dist: praat-parselmouth>=0.4.2
Requires-Dist: pyworld
Requires-Dist: torchcrepe
Requires-Dist: fairseq
Requires-Dist: joblib>=1.1.0
Requires-Dist: numba==0.56.4
Requires-Dist: numpy==1.23.5
Requires-Dist: scipy
Requires-Dist: librosa==0.9.1
Requires-Dist: llvmlite==0.39.0
Requires-Dist: fairseq==0.12.2
Requires-Dist: faiss-cpu==1.7.3
Requires-Dist: gradio==3.34.0
Requires-Dist: Cython
Requires-Dist: pydub>=0.25.1
Requires-Dist: soundfile>=0.12.1
Requires-Dist: ffmpeg-python>=0.2.0
Requires-Dist: tensorboardX
Requires-Dist: Jinja2>=3.1.2
Requires-Dist: json5
Requires-Dist: Markdown
Requires-Dist: matplotlib>=3.7.0
Requires-Dist: matplotlib-inline>=0.1.3
Requires-Dist: praat-parselmouth>=0.4.2
Requires-Dist: Pillow>=9.1.1
Requires-Dist: resampy>=0.4.2
Requires-Dist: scikit-learn
Requires-Dist: tensorboard
Requires-Dist: tqdm>=4.63.1
Requires-Dist: tornado>=6.1
Requires-Dist: Werkzeug>=2.2.3
Requires-Dist: uc-micro-py>=1.0.1
Requires-Dist: sympy>=1.11.1
Requires-Dist: tabulate>=0.8.10
Requires-Dist: PyYAML>=6.0
Requires-Dist: pyasn1>=0.4.8
Requires-Dist: pyasn1-modules>=0.2.8
Requires-Dist: fsspec>=2022.11.0
Requires-Dist: absl-py>=1.2.0
Requires-Dist: audioread
Requires-Dist: uvicorn>=0.21.1
Requires-Dist: colorama>=0.4.5
Requires-Dist: pyworld==0.3.2
Requires-Dist: httpx
Requires-Dist: onnxruntime; sys_platform == "darwin"
Requires-Dist: onnxruntime-gpu; sys_platform != "darwin"
Requires-Dist: torchcrepe==0.0.20
Requires-Dist: fastapi==0.88
Requires-Dist: ffmpy==0.3.1
Requires-Dist: python-dotenv>=1.0.0
Requires-Dist: av==11.0.0

# Fast-TTS

Fast-TTS is a module that offers a simple api in order to generate a speech from text. 


## Requirements
- Python 3.9
- CUDA enabled GPU with [PyTorch](https://pytorch.org/get-started/locally/) installed.


## How to add Voices

The following steps show how to add voices.
- Create a folder with the speaker name '/MyVoice'. Here 'MyVoice' is the name of the speaker that you wish to add.
- Find 1-3 audio samples of the speaker, those samples should be ~1min in length and be .wav files. The clearer the voice, the better the generated audio will be.
- Add those audio sampples to the speaker folder that was previously created.
- Add the .index and .pth files for the speaker model. Name them 'MyVoice.index' and 'MyVoice.pth'.
- You can either get the .index and .pth files from trained RVC models, or you can train your own model.
