Request : Support more than 2 persons in the transcript and audio

[pfloresl]

I imagine this is not supported, but it would be great if we could enable more than two roles in a conversation about the uploaded content.

[souzatharsis]

This is interesting. Could you please elaborate why this is important for your use case? <http://linkedin.com/in/tharsissouza>

…

On Tue, Oct 29, 2024 at 6:00 PM pablo flores ***@***.***> wrote: I imagine this is not supported, but it would be great if we could enable more than two roles in a conversation about the uploaded content. — Reply to this email directly, view it on GitHub <#130>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ADTMY3P34SH3F75TS4NJIPLZ57ZP5AVCNFSM6AAAAABQ2XSWEGVHI2DSMVQWIX3LMV43ASLTON2WKOZSGYZDEMZSGA3DAOA> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[pfloresl]

Yes, a mechanism for learning is to, for example, have philosophers, artists, and scientists have a conversation about a topic, each bringing up their background. Each will show to the others something that they may not be seeing. Many times I listen to programs that involve 2-5 people, each representing their world. This provides a rich conversation

…

On Tue, Oct 29, 2024, at 2:02 PM, Tharsis Souza wrote: This is interesting. Could you please elaborate why this is important for your use case? <http://linkedin.com/in/tharsissouza> On Tue, Oct 29, 2024 at 6:00 PM pablo flores ***@***.***> wrote: > I imagine this is not supported, but it would be great if we could enable > more than two roles in a conversation about the uploaded content. > > — > Reply to this email directly, view it on GitHub > <#130>, or unsubscribe > <https://github.com/notifications/unsubscribe-auth/ADTMY3P34SH3F75TS4NJIPLZ57ZP5AVCNFSM6AAAAABQ2XSWEGVHI2DSMVQWIX3LMV43ASLTON2WKOZSGYZDEMZSGA3DAOA> > . > You are receiving this because you are subscribed to this thread.Message > ID: ***@***.***> > — Reply to this email directly, view it on GitHub <#130 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ABA27S4EZTZWE5FFJK3BM3DZ57ZYHAVCNFSM6AAAAABQ2XSWEGVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDINBVGMZDKMJVGA>. You are receiving this because you authored the thread.Message ID: ***@***.***>

[souzatharsis]

Thanks; that's helpful. We should generalize the number of speakers. <http://linkedin.com/in/tharsissouza> On Tue, Oct 29, 2024 at 6:13 PM pablo flores ***@***.***> wrote:

…

Yes, a mechanism for learning is to, for example, have philosophers, artists, and scientists have a conversation about a topic, each bringing up their background. Each will show to the others something that they may not be seeing. Many times I listen to programs that involve 2-5 people, each representing their world. This provides a rich conversation On Tue, Oct 29, 2024, at 2:02 PM, Tharsis Souza wrote: > > > This is interesting. Could you please elaborate why this is important for > your use case? > > <http://linkedin.com/in/tharsissouza> > > > On Tue, Oct 29, 2024 at 6:00 PM pablo flores ***@***.***> > wrote: > > > I imagine this is not supported, but it would be great if we could enable > > more than two roles in a conversation about the uploaded content. > > > > — > > Reply to this email directly, view it on GitHub > > <#130>, or unsubscribe > > < https://github.com/notifications/unsubscribe-auth/ADTMY3P34SH3F75TS4NJIPLZ57ZP5AVCNFSM6AAAAABQ2XSWEGVHI2DSMVQWIX3LMV43ASLTON2WKOZSGYZDEMZSGA3DAOA> > > . > > You are receiving this because you are subscribed to this thread.Message > > ID: ***@***.***> > > > > — > Reply to this email directly, view it on GitHub < #130 (comment)>, or unsubscribe < https://github.com/notifications/unsubscribe-auth/ABA27S4EZTZWE5FFJK3BM3DZ57ZYHAVCNFSM6AAAAABQ2XSWEGVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDINBVGMZDKMJVGA>. > You are receiving this because you authored the thread.Message ID: ***@***.***> > — Reply to this email directly, view it on GitHub <#130 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ADTMY3L4GY6YEXCOPJHX3Q3Z5725ZAVCNFSM6AAAAABQ2XSWEGVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDINBVGM2DANJYGE> . You are receiving this because you commented.Message ID: ***@***.***>

[brumar]

Hi @souzatharsis
I thought a bit about this and I think the dev branch supports this (but the current configuration files won't work, nor the llm backend that was set up emulate the current default transcript engine) .

[souzatharsis]

Thanks @brumar ! I will think about a way to add this inspired by your code and kindly ask you to review (but only after I manage to Refactor some other more foundational components).

[brumar]

Sure, please use a MP when you need my attention, I have many podcastfy notifications and I could miss it.