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

Streaming inference for XTTS 🚀 #3035

Merged
merged 13 commits into from
Oct 6, 2023
Merged

Streaming inference for XTTS 🚀 #3035

merged 13 commits into from
Oct 6, 2023

Conversation

WeberJulian
Copy link
Contributor

@WeberJulian WeberJulian commented Oct 6, 2023

  • Replace the slow diffusion model with our own hifigan variant model
  • Implement deepspeed as an option for huge GPT speedup
  • Add support for streaming output audio
  • Corresponding doc
  • Toy streaming server example
  • Additional XTTS Tests

@erogol erogol changed the title Faster inference for XTTS 🚀 Streaming inference for XTTS 🚀 Oct 6, 2023
@gorkemgoknar gorkemgoknar marked this pull request as ready for review October 6, 2023 16:09
@erogol erogol merged commit e5e0cbf into dev Oct 6, 2023
48 checks passed
David-bfg pushed a commit to David-bfg/TTS that referenced this pull request Oct 9, 2023
erogol added a commit that referenced this pull request Oct 16, 2023
* add add cli options for play and speed
--play argument uses simpleaudio to play the tts wav
--speed <float 0.0-2.0> passes speed argument to Coqui Studio models

* remove simpleaudio not referenced in file

* fix simpleaudio dependency version

* add ALSA headers for simpleaudio compilation

* Dockerfile ALSA headers for simpleaudio

* base changes to use stdout instead of play audio
Considering conversion to pipe wav data for audio playback with ohter program
like aplay.

This is incomplete code. Using to get feedback before proceeding with
implementation.

* remove play for pipe_out arg that suppresses stdout
removed play and simpleaudio dependency in place of pipe
fuctionality to allow passing wav file data to a program
dedicated to playing audio.

* scipy.io.wavfile.write fails with /dev/null target

* Streaming inference for XTTS 🚀 (#3035)

* v0.17.7

* Redownload XTTS with the local and remote config do not match

* Remove unused method

* Print a message when it is already donwloaded

* Try-except to present error when the user dont have connection

* Fix style

* 0.17.8

* v0.17.8

---------

Co-authored-by: Julian Weber <julian.weber@hotmail.fr>
Co-authored-by: Eren Gölge <erogol@hotmail.com>
Co-authored-by: Edresson Casanova <edresson1@gmail.com>
Co-authored-by: ggoknar <ggoknar@coqui.ai>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants