glow-speak is a fast, local, neural text to speech system that uses eSpeak-ng as a text/phoneme front-end.

Last update: Dec 25, 2022

Related tags

Overview

Glow-Speak

glow-speak is a fast, local, neural text to speech system that uses eSpeak-ng as a text/phoneme front-end.

Installation

git clone https://github.com/rhasspy/glow-speak.git
cd glow-speak/

python3 -m venv .venv
source .venv/bin/activate
pip3 install --upgrade pip
pip3 install --upgrade setuptools wheel
pip3 install -f 'https://synesthesiam.github.io/prebuilt-apps/' -r requirements.txt

python3 setup.py develop
glow-speak --version

Voices

The following languages/voices are supported:

German
- de_thorsten
Chinese
- cmn_jing_li
Greek
- el_rapunzelina
English
- en-us_ljspeech
- en-us_mary_ann
Spanish
- es_tux
Finnish
- fi_harri_tapani_ylilammi
French
- fr_siwis
Hungarian
- hu_diana_majlinger
Italian
- it_riccardo_fasol
Korean
- ko_kss
Dutch
- nl_rdh
Russian
- ru_nikolaev
Swedish
- sv_talesyntese
Swahili
- sw_biblia_takatifu
Vietnamese
- vi_vais1000

Usage

Download Voices

glow-speak-download de_thorsten

Command-Line Synthesis

glow-speak -v en-us_mary_ann 'This is a test.' --output-file test.wav

HTTP Server

glow-speak-http-server --debug

Visit http://localhost:5002

Socket Server

Start the server:

glow-speak-socket-server --voice en-us_mary_ann --socket /tmp/glow-speak.sock

From a separate terminal:

echo 'This is a test.' | bin/glow-speak-socket-client --socket /tmp/glow-speak.sock | xargs aplay

Lines from client to server are synthesized, and the path to the WAV file is returned (usually in /tmp).

You might also like...

End-to-End Speech Processing Toolkit

ESPnet: end-to-end speech processing toolkit system/pytorch ver. 1.0.1 1.1.0 1.2.0 1.3.1 1.4.0 1.5.1 1.6.0 1.7.1 1.8.1 ubuntu18/python3.8/pip ubuntu18

5.9k Jan 3, 2023

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

OpenSpeech provides reference implementations of various ASR modeling papers and three languages recipe to perform tasks on automatic speech recogniti

26 Dec 14, 2022

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

OpenSpeech provides reference implementations of various ASR modeling papers and three languages recipe to perform tasks on automatic speech recogniti

86 Jun 11, 2021

Athena is an open-source implementation of end-to-end speech processing engine.

Athena is an open-source implementation of end-to-end speech processing engine. Our vision is to empower both industrial application and academic research on end-to-end models for speech processing. To make speech processing available to everyone, we're also releasing example implementation and recipe on some opensource dataset for various tasks (Automatic Speech Recognition, Speech Synthesis, Voice Conversion, Speaker Recognition, etc).

34 Sep 8, 2022

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

🤗 Contributing to OpenSpeech 🤗 OpenSpeech provides reference implementations of various ASR modeling papers and three languages recipe to perform ta

513 Jan 3, 2023

SHAS: Approaching optimal Segmentation for End-to-End Speech Translation

SHAS: Approaching optimal Segmentation for End-to-End Speech Translation In this repo you can find the code of the Supervised Hybrid Audio Segmentatio

21 Dec 20, 2022

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

CRNN paper：An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition 1. create your ow

3 Apr 2, 2022

Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning on image-text and video-text tasks

Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning on image-text and video-text tasks. It takes raw videos/images + text as inputs, and outputs task predictions. ClipBERT is designed based on 2D CNNs and transformers, and uses a sparse sampling strategy to enable efficient end-to-end video-and-language learning.

612 Jan 4, 2023

Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge

Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge This is an implementation of the paper,

19 Oct 14, 2022

Comments

AssertionError on web interface (only) - and Raspberry Pi Bullseye test

Hi Micheal,

great work again! :smiley:

I just saw this repository and thought I'd give it a try on my freshly installed Raspberry Pi 4 with 32bit Raspberry Pi OS Bullseye (Debian 11). Installation almost finished without errors! :partying_face: ... I just had to fix one thing: sudo apt-get install libatlas-base-dev After 15min I was already generating audio :grin: :+1:

When I tested en mary_ann and thorsten_de via the web interface I got this error as soon as my test sentence ended with a question mark:

DEBUG:glow-speak:ɪ_z ð_ɪ_s ɐ_n_ˈʌ_ð_ɚ t_ˈɛ_s_t? .
ERROR:glow_speak.http_server:
Traceback (most recent call last):
  File "/home/pi/glow-speak/.venv/lib/python3.9/site-packages/quart/app.py", line 1490, in full_dispatch_request
    result = await self.dispatch_request(request_context)
  File "/home/pi/glow-speak/.venv/lib/python3.9/site-packages/quart/app.py", line 1536, in dispatch_request
    return await self.ensure_async(handler)(**request_.view_args)
  File "/home/pi/glow-speak/glow_speak/http_server.py", line 484, in app_say
    wav_bytes = await text_to_wav(text, voice, **tts_args)
  File "/home/pi/glow-speak/glow_speak/http_server.py", line 323, in text_to_wav
    text_ids = text_to_ids(
  File "/home/pi/glow-speak/glow_speak/__init__.py", line 110, in text_to_ids
    text_ids = phonemes2ids(
  File "/home/pi/glow-speak/.venv/lib/python3.9/site-packages/phonemes2ids/__init__.py", line 190, in phonemes2ids
    maybe_extend_ids(sub_phoneme, word_ids, append_list=False)
  File "/home/pi/glow-speak/.venv/lib/python3.9/site-packages/phonemes2ids/__init__.py", line 108, in maybe_extend_ids
    maybe_ids = missing_func(phoneme)
  File "/home/pi/glow-speak/glow_speak/__init__.py", line 59, in guess_ids
    typing.List[Phoneme], guess_phonemes(phoneme, self.to_phonemes)
  File "/home/pi/glow-speak/.venv/lib/python3.9/site-packages/gruut_ipa/accent.py", line 159, in guess_phonemes
    assert dist_split is not None
AssertionError

Maybe some encoding error when reading the web input?

Speed seems pretty good, comparable to Larynx I'd say :+1: and I noticed the pronunciations have been improved for German :clap: :sunglasses:

opened by fquirin 0

Releases(v1.0)

v1.0(Oct 20, 2021)

Source code(tar.gz)
Source code(zip)
cmn_jing_li.tar.gz(101.49 MB)
de_thorsten.tar.gz(101.59 MB)
el_rapunzelina.tar.gz(101.34 MB)
en-us_ljspeech.tar.gz(101.66 MB)
en-us_mary_ann.tar.gz(101.69 MB)
es_tux.tar.gz(101.61 MB)
fi_harri_tapani_ylilammi.tar.gz(101.46 MB)
fr_siwis.tar.gz(101.59 MB)
hu_diana_majlinger.tar.gz(101.47 MB)
it_riccardo_fasol.tar.gz(101.70 MB)
ko_kss.tar.gz(101.58 MB)
nl_rdh.tar.gz(101.60 MB)
ru_nikolaev.tar.gz(101.64 MB)
sv_talesyntese.tar.gz(101.42 MB)
sw_biblia_takatifu.tar.gz(101.71 MB)
vi_vais1000.tar.gz(101.28 MB)

Owner

Rhasspy

Offline voice assistant

GitHub Repository

This is a Prototype of an Ai ChatBot "Tea and Coffee Supplier" using python.

Ai-ChatBot-Python A chatbot is an intelligent system which can hold a conversation with a human using natural language in real time. Due to the rise o

1 Oct 30, 2021

Fine-tuning scripts for evaluating transformer-based models on KLEJ benchmark.

The KLEJ Benchmark Baselines The KLEJ benchmark (Kompleksowa Lista Ewaluacji Językowych) is a set of nine evaluation tasks for the Polish language und

17 Oct 18, 2022

A Facebook Messenger Chatbot using NLP

A Facebook Messenger Chatbot using NLP This project is about creating a messenger chatbot using basic NLP techniques and models like Logistic Regressi

6 Nov 20, 2022

PyTorch implementation of NATSpeech: A Non-Autoregressive Text-to-Speech Framework

A Non-Autoregressive Text-to-Speech (NAR-TTS) framework, including official PyTorch implementation of PortaSpeech (NeurIPS 2021) and DiffSpeech (AAAI 2022)

760 Jan 03, 2023

Voilà turns Jupyter notebooks into standalone web applications

Rendering of live Jupyter notebooks with interactive widgets. Introduction Voilà turns Jupyter notebooks into standalone web applications. Unlike the

4.5k Jan 03, 2023

Code release for "COTR: Correspondence Transformer for Matching Across Images"

COTR: Correspondence Transformer for Matching Across Images This repository contains the inference code for COTR. We plan to release the training code

358 Dec 24, 2022

ConferencingSpeech2022; Non-intrusive Objective Speech Quality Assessment (NISQA) Challenge

ConferencingSpeech 2022 challenge This repository contains the datasets list and scripts required for the ConferencingSpeech 2022 challenge. For more

21 Dec 02, 2022

GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training

GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training Code and model from our AAAI 2021 paper

83 Jan 09, 2023

Python wrapper for Stanford CoreNLP tools v3.4.1

Python interface to Stanford Core NLP tools v3.4.1 This is a Python wrapper for Stanford University's NLP group's Java-based CoreNLP tools. It can eit

610 Sep 07, 2022

A sentence aligner for comparable corpora

About Yalign is a tool for extracting parallel sentences from comparable corpora. Statistical Machine Translation relies on parallel corpora (eg.. eur

128 Aug 24, 2022

SinglepassTextCluster, an TextCluster tools based on Singlepass cluster algorithm that use tfidf vector and doc2vec，which can be used for individual real-time corpus cluster task。基于single-pass算法思想的自动文本聚类小组件，内置tfidf和doc2vec两种文本向量方法，可自动输出聚类数目、类簇文档集合和簇类大小，用于自有实时数据的聚类任务。

项目的背景 SinglepassTextCluster, an TextCluster tool based on Singlepass cluster algorithm that use tfidf vector and doc2vec，which can be used for individ

34 Dec 18, 2022

glow-speak is a fast, local, neural text to speech system that uses eSpeak-ng as a text/phoneme front-end.

Related tags

Overview

Glow-Speak

Installation

Voices

Usage

Download Voices

Command-Line Synthesis

HTTP Server

Socket Server

You might also like...

End-to-End Speech Processing Toolkit

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

Athena is an open-source implementation of end-to-end speech processing engine.

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

SHAS: Approaching optimal Segmentation for End-to-End Speech Translation

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning on image-text and video-text tasks

Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge

Comments

AssertionError on web interface (only) - and Raspberry Pi Bullseye test

Releases(v1.0)

v1.0(Oct 20, 2021)

Owner

Rhasspy

This is a Prototype of an Ai ChatBot "Tea and Coffee Supplier" using python.

Fine-tuning scripts for evaluating transformer-based models on KLEJ benchmark.

A Facebook Messenger Chatbot using NLP

PyTorch implementation of NATSpeech: A Non-Autoregressive Text-to-Speech Framework

Voilà turns Jupyter notebooks into standalone web applications

Code release for "COTR: Correspondence Transformer for Matching Across Images"

ConferencingSpeech2022; Non-intrusive Objective Speech Quality Assessment (NISQA) Challenge

GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training

Python wrapper for Stanford CoreNLP tools v3.4.1

A sentence aligner for comparable corpora

Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"

Extract Keywords from sentence or Replace keywords in sentences.

This is the source code of RPG (Reward-Randomized Policy Gradient)

YACLC - Yet Another Chinese Learner Corpus

[AAAI 21] Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning

Code for paper "Role-oriented Network Embedding Based on Adversarial Learning between Higher-order and Local Features"

Phrase-Based & Neural Unsupervised Machine Translation

Two-stage text summarization with BERT and BART

An end to end ASR Transformer model training repo