Data

Tools

Indexes

Applications

Experiments

Open Source Science

en-tts

Command-line interface and Python library for synthesizing English texts into speech.

https://github.com/stefantaubert/en-tts

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 7 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (10.5%) to scientific vocabulary

Keywords

english speech speech-synthesis tacotron text-to-speech tts waveglow
Last synced: 6 months ago · JSON representation ·

Repository

Command-line interface and Python library for synthesizing English texts into speech.

Basic Info
Statistics
  • Stars: 4
  • Watchers: 1
  • Forks: 1
  • Open Issues: 0
  • Releases: 2
Topics
english speech speech-synthesis tacotron text-to-speech tts waveglow
Created about 2 years ago · Last pushed almost 2 years ago
Metadata Files
Readme Changelog Contributing License Code of conduct Citation

README.md

en-tts

PyPI PyPI Hugging Face 🤗 pytorch MIT PyPI PyPI PyPI DOI

Web app, command-line interface and Python library for synthesizing English texts into speech.

Installation

sh pip install en-tts --user

Usage as web app

Visit 🤗 Hugging Face for a live demo.

Screenshot Hugging Face

You can also run it locally be executing en-tts-web in CLI and opening your browser on http://127.0.0.1:7860.

Usage as CLI

sh en-tts-cli synthesize "When the sunlight strikes raindrops in the air, they act as a prism and form a rainbow."

The output can be listened here.

Usage as library

```py from pathlib import Path from tempfile import gettempdir

from entts import Synthesizer, Transcriber, normalizeaudio, save_audio

text = "When the sunlight strikes raindrops in the air, they act as a prism and form a rainbow."

transcriber = Transcriber() synthesizer = Synthesizer()

textipa = transcriber.transcribetoipa(text) audio = synthesizer.synthesize(textipa)

tmpdir = Path(gettempdir()) saveaudio(audio, tmp_dir / "output.wav")

Optional: normalize output

normalizeaudio(tmpdir / "output.wav", tmpdir / "outputnorm.wav") ```

Model info

The used TTS model is published here.

Evaluation results:

  • MOS naturalness: 3.55 ± 0.28 (GT: 4.17 ± 0.23)
  • MOS intelligibility: 4.44 ± 0.24 (GT: 4.63 ± 0.19)
  • Mean MCD-DTW: 29.15
  • Mean penalty: 0.1018

Phoneme set

  • Vowels: i, u, æ, ɑ, ɔ, ə, ɛ, ɪ, ʊ, ʌ
  • Diphthongs: aɪ, aʊ, eɪ, oʊ, ɔɪ
  • R-colored vowels: ɔr, ər, ɛr, ɪr, ʊr, ʌr
  • Consonants: b, d, dʒ, f, h, j, k, l, m, n, p, r, s, t, tʃ, v, w, z, ð, ŋ, ɡ, ʃ, θ
  • Breaks:
    • SIL0 (no break)
    • SIL1 (short break)
    • SIL2 (break)
    • SIL3 (long break)
  • Special characters: . ? ! , : ; - — " ' ( ) [ ]

Each vowel, diphthong, r-colored vowel and consonant can have one of these duration markers:

  • ˘ -> very short, e.g., oʊ˘
  • nothing -> normal, e.g., oʊ
  • ˑ -> half long, e.g., oʊˑ
  • ː -> long, e.g., oʊː

Furthermore, each vowel, diphthong and r-colored vowel can have a leading stress symbol attached:

  • ˈ -> primary stress, e.g., ˈoʊ
  • ˌ -> secondary stress, e.g., ˌoʊ
  • nothing -> no stress, e.g., oʊ

Stress and duration markers can be combined, e.g., ˌoʊː

Citation

If you want to cite this repo, you can use the BibTeX-entry generated by GitHub (see About => Cite this repository).

Acknowledgments

Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) – Project-ID 416228727 – CRC 1410

The authors gratefully acknowledge the GWK support for funding this project by providing computing time through the Center for Information Services and HPC (ZIH) at TU Dresden.

The authors are grateful to the Center for Information Services and High Performance Computing [Zentrum fur Informationsdienste und Hochleistungsrechnen (ZIH)] at TU Dresden for providing its facilities for high throughput calculations.

Owner

  • Name: Stefan Taubert
  • Login: stefantaubert
  • Kind: user
  • Location: Chemnitz, Germany
  • Company: Chemnitz University of Technology

Currently I am working on my PhD about the topic of speech synthesis at Chemnitz University of Technology.

Citation (CITATION.cff) 

cff-version: 1.2.0
title: en-tts
abstract: Web app, command-line interface and Python library for synthesizing English texts into speech.
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - email: github@stefantaubert.com
    given-names: Stefan
    family-names: Taubert
    affiliation: Chemnitz University of Technology
    orcid: 'https://orcid.org/0000-0002-4932-2874'
    website: 'https://stefantaubert.com/'
version: 0.0.2
date-released: 2024-04-23
license: MIT
url: https://github.com/stefantaubert/en-tts
doi: 10.5281/zenodo.11032264

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 23 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 0
  • Total versions: 2
  • Total maintainers: 1
pypi.org: en-tts

Web app, command-line interface and Python library for synthesizing English texts into speech.

  • Versions: 2
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 23 Last month
Rankings
Dependent packages count: 10.0%
Average: 37.8%
Dependent repos count: 65.7%
Maintainers (1)
stefantaubert
Last synced: 6 months ago

Dependencies

Pipfile pypi
  • autoflake * develop
  • autopep8 * develop
  • build * develop
  • en-tts * develop
  • isort * develop
  • pycodestyle * develop
  • pylint * develop
  • pytest * develop
  • rope * develop
  • twine * develop
  • wget * develop
  • TextGrid >=1.5
  • dict-from-dict *
  • dict-from-g2pe *
  • english-text-normalization *
  • matplotlib >=3.5.0
  • numpy >=1.18.5
  • ordered-set >=4.1.0
  • pandas >=1.4.0
  • pronunciation-dictionary *
  • pronunciation-dictionary-utils *
  • scipy >=1.8.0
  • tacotron *
  • tqdm >=4.63.0
  • waveglow-cli *
Pipfile.lock pypi
  • astroid ==3.0.2 develop
  • autoflake ==2.2.1 develop
  • autopep8 ==2.0.4 develop
  • build ==1.0.3 develop
  • certifi ==2023.11.17 develop
  • cffi ==1.16.0 develop
  • charset-normalizer ==3.3.2 develop
  • contourpy ==1.2.0 develop
  • cryptography ==41.0.7 develop
  • cycler ==0.12.1 develop
  • dill ==0.3.7 develop
  • docutils ==0.20.1 develop
  • exceptiongroup ==1.2.0 develop
  • fonttools ==4.47.2 develop
  • idna ==3.6 develop
  • importlib-metadata ==7.0.1 develop
  • iniconfig ==2.0.0 develop
  • isort ==5.13.2 develop
  • jaraco.classes ==3.3.0 develop
  • jeepney ==0.8.0 develop
  • keyring ==24.3.0 develop
  • kiwisolver ==1.4.5 develop
  • markdown-it-py ==3.0.0 develop
  • matplotlib ==3.8.2 develop
  • mccabe ==0.7.0 develop
  • mdurl ==0.1.2 develop
  • more-itertools ==10.2.0 develop
  • nh3 ==0.2.15 develop
  • numpy ==1.26.3 develop
  • ordered-set ==4.1.0 develop
  • packaging ==23.2 develop
  • pandas ==2.1.4 develop
  • pillow ==10.2.0 develop
  • pkginfo ==1.9.6 develop
  • platformdirs ==4.1.0 develop
  • pluggy ==1.3.0 develop
  • pycodestyle ==2.11.1 develop
  • pycparser ==2.21 develop
  • pyflakes ==3.2.0 develop
  • pygments ==2.17.2 develop
  • pylint ==3.0.3 develop
  • pyparsing ==3.1.1 develop
  • pyproject-hooks ==1.0.0 develop
  • pytest ==7.4.4 develop
  • python-dateutil ==2.8.2 develop
  • pytoolconfig ==1.3.1 develop
  • pytz ==2023.3.post1 develop
  • readme-renderer ==42.0 develop
  • requests ==2.31.0 develop
  • requests-toolbelt ==1.0.0 develop
  • rfc3986 ==2.0.0 develop
  • rich ==13.7.0 develop
  • rope ==1.11.0 develop
  • scipy ==1.11.4 develop
  • secretstorage ==3.3.3 develop
  • six ==1.16.0 develop
  • textgrid ==1.5 develop
  • tomli ==2.0.1 develop
  • tomlkit ==0.12.3 develop
  • tqdm ==4.66.1 develop
  • twine ==4.0.2 develop
  • typing-extensions ==4.9.0 develop
  • tzdata ==2023.4 develop
  • unknown * develop
  • urllib3 ==2.1.0 develop
  • wget ==3.2 develop
  • zipp ==3.17.0 develop
  • contourpy ==1.2.0
  • cycler ==0.12.1
  • fonttools ==4.47.2
  • kiwisolver ==1.4.5
  • matplotlib ==3.8.2
  • numpy ==1.26.3
  • ordered-set ==4.1.0
  • packaging ==23.2
  • pandas ==2.1.4
  • pillow ==10.2.0
  • pyparsing ==3.1.1
  • python-dateutil ==2.8.2
  • pytz ==2023.3.post1
  • scipy ==1.11.4
  • six ==1.16.0
  • textgrid ==1.5
  • tqdm ==4.66.1
  • tzdata ==2023.4
pyproject.toml pypi
  • TextGrid >=1.5
  • matplotlib >=3.5.0
  • numpy >=1.18.5
  • ordered_set >=4.1.0
  • pandas >=1.4.0
  • scipy >=1.8.0
  • tqdm >=4.63.0