Josh Meyer

Hi there! This is great research / code, and it would be great if there were an explicit (and hopefully `permissive`) license with it. You can find good info on...

Compile problems in Ubuntu artful

2

``` (deepspeech-venv) josh@stealth:~/git/DeepSpeech/kenlm/build$ make [ 0%] Building CXX object util/CMakeFiles/kenlm_util.dir/double-conversion/bignum-dtoa.cc.o [ 1%] Building CXX object util/CMakeFiles/kenlm_util.dir/double-conversion/bignum.cc.o [ 2%] Building CXX object util/CMakeFiles/kenlm_util.dir/double-conversion/cached-powers.cc.o [ 2%] Building CXX object util/CMakeFiles/kenlm_util.dir/double-conversion/diy-fp.cc.o [ 3%]...

Hi, Jonathan, I'm wondering how you would implement at Mutli-Task model such as what you've got, but for multiple data sets. The alternating output layers you've got shown seem good,...

[Bug] `list_speaker_idx` and throws error (CLI, v0.22.0)

3

### Describe the bug trying to list studio speakers from the CLI, and getting errors (macOS, CPU) ### To Reproduce 1. pip install -U TTS 2. tts --model_name tts_models/multilingual/multi-dataset/xtts_v2 --list_speaker_idx...

add License

1

Very cool work! You should add a license so people know how they may use it:)

Added modern neural net speech synthesis with Merlin and Ossian

3

Added three lines under Text-to-speech for Merlin + Ossian + the more traditional Festival

what does "libfvad" stand for?

1

I guess "Library for Voice Activity Detection", but I'm not sure... It would be nice in the README

better arg handling

1

should be able to run `python data_checks.py -h`, and should have smarter arg handling in general

wanted features

1

add VAD + SNR

Nice project! You should add a license so people know how they can use it