Open howardbaik opened 1 year ago
See https://github.com/yihui/xaringan/blob/8dcfa3f9a0d7f921176d9fde90e2a765c76ee8e7/R/render.R#L407 Best, John
On Thu, Jun 1, 2023 at 2:01 PM Howard Baek @.***> wrote:
An idea from @seankross https://github.com/seankross : Move all the Coqui TTS functionality into a separate R package, create a Docker image with Coqui TTS installed, and call tts_coqui() on the Docker image. Not sure if I described this correctly, but that's the general idea.
— Reply to this email directly, view it on GitHub https://github.com/jhudsl/text2speech/issues/32, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAIGPLQPDTY6IMF7G6NR77DXJDKGXANCNFSM6AAAAAAYXIZXRE . You are receiving this because you are subscribed to this thread.Message ID: @.***>
See https://github.com/yihui/xaringan/blob/8dcfa3f9a0d7f921176d9fde90e2a765c76ee8e7/R/render.R#L407 Best, John … On Thu, Jun 1, 2023 at 2:01 PM Howard Baek @.> wrote: An idea from @seankross https://github.com/seankross : Move all the Coqui TTS functionality into a separate R package, create a Docker image with Coqui TTS installed, and call tts_coqui() on the Docker image. Not sure if I described this correctly, but that's the general idea. — Reply to this email directly, view it on GitHub <#32>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAIGPLQPDTY6IMF7G6NR77DXJDKGXANCNFSM6AAAAAAYXIZXRE . You are receiving this because you are subscribed to this thread.Message ID: @.>
Thank you for sharing! I'll take a look at this.
I think that the coqui functionality of text2speech would be used by users who have successfully downloaded coqui tts. For those without coqui tts on their systems, we could direct them to this R package + docker combination.
Another reason to have a standalone Coqui R package: it would be cool to do speech-to-text in R too.
I looked quickly at Coqui STT, and it looks like they are no longer actively maintaining it, but do have a command line client.
Here's my STT project, a wrapper around OpenAI Whisper: https://github.com/howardbaek/audrey
An idea from @seankross :
Move all the Coqui TTS functionality into a separate R package, create a Docker image with Coqui TTS installed, and call
tts_coqui()
on the Docker image. Not sure if I described this correctly, but that's the general idea.The R package would be called roqui 😄