v0.1.3

[erogol]

🐸 v0.1.3

🐞Bug Fixes

• Fix Tacotron stopnet training

  Models trained after v0.1 had the problem that the stopnet was not trained. It caused models not to generate audio
  at evaluation and inference time.

• Fix test_run at training. (👑 @WeberJulian)

  In training 🐸 TTS would skip the test_run and not generate test audio samples. Now it is fixed :).

💾 Code updates

• Refactoring in compute_embeddings.py for efficiency and compatibility with the latest speaker encoder. (👑 @Edresson)

🚀 Model releases

• New Fullband-MelGAN model for Throsten German dataset. (👑 @thorstenMueller)

[mbarnig]

I installed this version to run some tests:

Traceback (most recent call last):
  File "TTS/server/server.py", line 10, in <module>
    from flask import Flask, render_template, request, send_file
ModuleNotFoundError: No module named 'flask'

[thorstenMueller]

Hi @mbarnig .
According to https://github.com/coqui-ai/TTS/releases the new version has not been released yet.

[mbarnig]

@thorstenMueller : I know, I installed the dev branch. I think the purpose of the present comment #674 is to get some early reactions before the release of the new version.

[erogol]

@mbarnig make sure you followed installation instructions. https://tts.readthedocs.io/en/latest/installation.html

[mbarnig]

@erogol : my fault. I was using the ancient command pip install -e . to install from source.

With

make system-deps
make install

the script python3 TTS/server/server.py works without error.
In the future I will always check if the documentation has been changed before raising an issue.
Thanks for your quick response.