Open Voice Technology Wiki - User contributions [en]

User talk:Nmstoker

2022-01-04T20:17:12Z

Nmstoker:

== Welcome to OpenVoice-Talk Wiki ==

Hi [[User:Nmstoker|Nmstoker]], thanks for joining here :-). Did you receive a mail notification that i've mentioned you here? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 20:26, 12 November 2021 (CET)

Hi Thorsten. Glad to be here :-)
Yes I did get an email about the mention (with your message included) [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 22:28, 12 November 2021 (CET)

Here's me attempting to mention you back:
[[User:Thorsten]] - did you get this? [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 22:30, 12 November 2021 (CET)
:Yes, i've seen a red notification symbol :-). But no mail notification. I'll check the config when mails will be send. --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 22:38, 12 November 2021 (CET)

== Bokeh analysis for TTS datasets ==

Hi Neil, when i remember right you had a notebook for printing some sort of Bokeh analysis for TTS datasets, or? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 19:46, 4 January 2022 (CET)

This doesn't seem to save all my replies... [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 21:15, 4 January 2022 (CET)

It seems I cannot include a link to it in GitHub [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 21:16, 4 January 2022 (CET)

The link needed is here, without https
github.com/mozilla/TTS/tree/af6f86252e6fe21fc02357fe681344f89d75a0ca/TTS/speaker_encoder [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 21:17, 4 January 2022 (CET)

User talk:Nmstoker

2022-01-04T20:16:40Z

Nmstoker:

User talk:Nmstoker

2022-01-04T20:15:49Z

Nmstoker:

User talk:Nmstoker

2021-11-12T21:30:54Z

Nmstoker:

User talk:Nmstoker

2021-11-12T21:28:11Z

Nmstoker:

Talk:Main Page

2021-11-12T13:15:11Z

Nmstoker:

== What infos on Mainpage? ==
I'm not sure which content is helpful on Mainpage. Any ideas? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 08:46, 20 October 2021 (CEST)

== General ideas on this wiki? ==

What do you think? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 21:22, 1 November 2021 (CET)

This seems a really worthwhile initiative.

Regarding the section for Voice related paper, maybe you already have thoughts on this, but I think it would be useful to recommend the kinds of detail desired (Title, Authors, DOI, source link(s), adding categories)

Open links (eg Arxiv) would be preferred over those to non-free / subscription sites.

Might also want to mention any preferences around pre-review/early access papers and handling updated versions and broken links. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:06, 12 November 2021 (CET)

Another general thought: where do you stand on inclusion of opinion/original information in the wiki?

Wikipedia is firmly about referencing information from sources, so they avoid hosting original information and only include things that are backed by references.

I'm guessing that there may be grounds for more flexibility here, but deciding where to draw the line is worth considering.

In a similar way, deciding where the line is between sharing knowledge vs excess promotion might need judgement. The key open source players do not strike me as being likely to over promote but there could be firms that aren't so reasonable, so having some kind of policy on this might help. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:15, 12 November 2021 (CET)

Talk:Main Page

2021-11-12T13:06:23Z

Nmstoker:

Recording tipps

2021-11-12T12:54:54Z

Nmstoker: Fixed some minor typos

[[Category:Recording tipps]]
[[Category:Lessons learned]]

When you plan to record a voice dataset to be used for a TTS model training you should check these tips and tricks:

* '''Use a good microphone and a quiet recording room setup''' (no computer fans, air conditioning, ...)
* Use a text corpus with cleaned numbers/abbreviations and good phoneme coverage
* Read in a neutral style, but with a natural speech flow and do not swallow up letters
* Adjust tone and pitch with punctuation
* Use a constant recording speed
* Check your recordings regularly in high volume for background noise
* Take breaks regularly and do not record more than four hours a day
* Record error free
* Investing in a quality interface and mic can make a big difference in quality. A 24 bit 96khz interface with a large diaphragm condenser can be had for about $200 USD.
* Record at the highest quality level practical. You can convert to lesser formats later, but you cannot up convert cleanly
* Review your work at regular intervals and compare with previous recording to ensure consistent quality
* Do not be afraid to ask for help! Getting feedback on your data early on can help prevent wasted effort.

Talk:Recording tipps

2021-11-12T12:51:31Z

Nmstoker: Created page with "Note: tips has just one p."

Note: tips has just one p.