leon-ai / leon

Hello, if i enable bidirectional decoder training script drops eror.
There is in train.py line 185
keep_avg.update_values({'avg_decoder_b_loss': loss_dict['decoder_backward_loss'].item(),
need to change on
keep_avg.update_values({'avg_decoder_b_loss': loss_dict['decoder_b_loss'].item(),

bug good first issue

Open

Support for Native Pytorch AMP

1

readbeyond / aeneas

Star

aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)

Updated Jul 15, 2020
Python

Rayhane-mamah / Tacotron-2

Star

DeepMind's Tacotron-2 Tensorflow implementation

python text-to-speech tensorflow paper speech-synthesis wavenet tacotron

Updated May 29, 2020
Python

NVIDIA / OpenSeq2Seq

Star

Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP

text-to-speech deep-learning tensorflow multi-node speech-synthesis speech-recognition seq2seq speech-to-text neural-machine-translation sequence-to-sequence language-model multi-gpu float16 mixed-precision

Updated Sep 25, 2020
Python

pndurette / gTTS

Star

Python library and CLI tool to interface with Google Translate's text-to-speech API

python text-to-speech speech tts gtts

Updated Oct 2, 2020
Python

TensorSpeech / TensorFlowTTS

Star

😝 TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, Korean, Chinese and Easy to adapt for other languages)

text-to-speech real-time tensorflow tts speech-synthesis seq2seq vocoder tflite neural-vocoder tensorflow2 fastspeech tacotron2 melgan multi-speaker-tts multiband-melgan mb-melgan fastspeech2 parallel-wavegan mobile-tts

Updated Oct 4, 2020
Python

fatchord / WaveRNN

Star

WaveRNN Vocoder + TTS

text-to-speech pytorch tts speech-synthesis tacotron wavernn neural-vocoder

Updated Sep 26, 2020
Python

CSTR-Edinburgh / merlin

Star

This is now the official location of the Merlin project.

python text-to-speech theano deep-learning tensorflow keras speech-synthesis voice-conversion merlin

Updated Mar 3, 2020
Python

DragonComputer / Dragonfire

Star

the open-source virtual assistant for Ubuntu based Linux distributions

nlp linux machine-learning text-to-speech ubuntu chatbot artificial-intelligence spacy speech-recognition personal-assistant speech-to-text kaldi virtual-assistant

Updated Sep 25, 2020
Python

codeforequity-at / botium-speech-processing

Star

Botium Speech Processing

text-to-speech speech-to-text botium

Updated Sep 10, 2020
JavaScript

Vonage / vonage-php-sdk-core

Star

Open

Add some documentation for the NCCO Builder

lornajane commented Sep 10, 2020

Expected Behavior

Find examples and instructions for the NCCO builder with this repo.

Current Behavior

No formal documentation, but some examples exist in the code snippets.

Possible Solution

Add a new section to the README to cover

good first issue hacktoberfest

Open

`Vonage\Numbers\Client::searchAvailable()` is passing filter as object instead of array to `parseParameters()`

2

espeak-ng / espeak-ng

Star

Open

All phonemes should have IPA entries phonemes file should have all of used ones

2

valdisvi commented May 30, 2020

If necessary, first look at Contribution guide.
To improve organization of phoneme definitions files (phonemes and ph_...) in phsource folder should have [IPA](https://en.wikipedia.org/wi

good first issue

Open