Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

test existing STT and TTS models #3

Open
3 tasks
rutsam opened this issue Feb 11, 2023 · 2 comments
Open
3 tasks

test existing STT and TTS models #3

rutsam opened this issue Feb 11, 2023 · 2 comments
Assignees

Comments

@rutsam
Copy link

rutsam commented Feb 11, 2023

Goal
Test existing TTS and STT model to find out which one is the best and which one shall we use

Metrics STT

  • Accuracy
  • Response time on CPU
    Metrics TTS
  • Naturalness
  • Comprehensibility
  • Response time on CPU

Definition of Done

  • Test existing TTS
  • Test existing STT
  • Present result to the team
@rutsam rutsam converted this from a draft issue Feb 11, 2023
@rutsam
Copy link
Author

rutsam commented Feb 11, 2023

We have decided to go with YourTTS for the TTS and NEMO conformer for STT, they are both fast, can run on CPU and much more accurate.
Here are the spaces for the STT and TTS

Next step is to have full metrics and create apis

@rutsam
Copy link
Author

rutsam commented Feb 18, 2023

We need better metrics for yourTTS and Nemo conformer CTC models before we consider it as done

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
Status: 🏗 In progress
Development

No branches or pull requests

3 participants