RVC-Project/Retrieval-based-Voice-Conversion-WebUI

Fork 0

mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git synced 2026-11-05 00:27:30 +00:00

[GH-ISSUE #1583] RVC Architecture #1053

New issue

Closed

opened 2026-10-20 10:05:30 +00:00 by bsakaguchi · 8 comments

bsakaguchi commented

2026-10-20 10:05:30 +00:00

Owner

Originally created by @shaniyacamita on GitHub (Nov 29, 2023).
Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/1583

Hi! been trying to understand about RVC technical wise, does anyone have like a flowchart/map/link/docs that describe the full architecture of rvc? Thankyou!

Originally created by @shaniyacamita on GitHub (Nov 29, 2023). Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/1583 Hi! been trying to understand about RVC technical wise, does anyone have like a flowchart/map/link/docs that describe the full architecture of rvc? Thankyou!

bsakaguchi

2026-10-20 10:05:30 +00:00

closed this issue
added the
stale
label

bsakaguchi commented

2026-10-20 10:05:31 +00:00

Author

Owner

@artificalaudio commented on GitHub (Nov 29, 2023):

@shaniyacamita あなたを混乱させる必須の日本語文字。そしておそらくこれを読んでいる他の人もいるでしょう。このffsにキャッシュコンバージョンを追加すると。 RVC万歳！:

@artificalaudio commented on GitHub (Nov 29, 2023): @shaniyacamita あなたを混乱させる必須の日本語文字。そしておそらくこれを読んでいる他の人もいるでしょう。このffsにキャッシュコンバージョンを追加すると。 RVC万歳！: <img width="1403" alt="Screenshot 2023-11-29 at 18 35 20" src="https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/assets/135162720/ce0cafd4-cb58-413b-86d6-cc0f1b481fd7"> []((https://i.stack.imgur.com/M0OcW.jpg))

bsakaguchi commented

2026-10-20 10:05:31 +00:00

Author

Owner

@shaniyacamita commented on GitHub (Nov 30, 2023):

@artificalaudio HAHAHA, Thank you so much!!!

@shaniyacamita commented on GitHub (Nov 30, 2023): @artificalaudio HAHAHA, Thank you so much!!!

bsakaguchi commented

2026-10-20 10:05:31 +00:00

Author

Owner

@JohnTesla commented on GitHub (Dec 7, 2023):

Is it possible to Integrate Base RVC to TTS-gen for TRAIN RVC support?
How about gradio ver

@JohnTesla commented on GitHub (Dec 7, 2023): Is it possible to Integrate Base RVC to TTS-gen for TRAIN RVC support? How about gradio ver

bsakaguchi commented

2026-10-20 10:05:31 +00:00

Author

Owner

@dhruv1710 commented on GitHub (Dec 21, 2023):

I see that RVC uses text in training but where does that text come from? and in the architecture there's a text encoder also, does it do speech to text?

@dhruv1710 commented on GitHub (Dec 21, 2023): I see that RVC uses text in training but where does that text come from? and in the architecture there's a text encoder also, does it do speech to text?

bsakaguchi commented

2026-10-20 10:05:31 +00:00

Author

Owner

@github-actions[bot] commented on GitHub (Apr 28, 2024):

This issue was closed because it has been inactive for 15 days since being marked as stale.

@github-actions[bot] commented on GitHub (Apr 28, 2024): This issue was closed because it has been inactive for 15 days since being marked as stale.

bsakaguchi commented

2026-10-20 10:05:31 +00:00

Author

Owner

@molo32 commented on GitHub (Aug 22, 2024):

Is there a better graph than this one? This one seems to lack information, for example,
what is posterior encoder?
Where is the error to be reduced?
What is target voice in the training process?

@molo32 commented on GitHub (Aug 22, 2024): Is there a better graph than this one? This one seems to lack information, for example, what is posterior encoder? Where is the error to be reduced? What is target voice in the training process?

bsakaguchi commented

2026-10-20 10:05:31 +00:00

Author

Owner

@AlirezaKamyab commented on GitHub (Jan 15, 2025):

I see that RVC uses text in training but where does that text come from? and in the architecture there's a text encoder also, does it do speech to text?

I don't suppose it is the text but it is the audio's features from Hubert model

@AlirezaKamyab commented on GitHub (Jan 15, 2025): > I see that RVC uses text in training but where does that text come from? and in the architecture there's a text encoder also, does it do speech to text? I don't suppose it is the text but it is the audio's features from Hubert model

bsakaguchi commented

2026-10-20 10:05:32 +00:00

Author

Owner

@AlirezaKamyab commented on GitHub (Jan 15, 2025):

@shaniyacamita あなたを混乱させる必須の日本語文字。そしておそらくこれを読んでいる他の人もいるでしょう。このffsにキャッシュコンバージョンを追加すると。 RVC万歳！:

I don't seem to find anything about Contrastive Learning in the code! Can you tell me where contrastive learning is implemented?

@AlirezaKamyab commented on GitHub (Jan 15, 2025): > @shaniyacamita あなたを混乱させる必須の日本語文字。そしておそらくこれを読んでいる他の人もいるでしょう。このffsにキャッシュコンバージョンを追加すると。 RVC万歳！: > > <img alt="Screenshot 2023-11-29 at 18 35 20" width="1403" src="https://private-user-images.githubusercontent.com/135162720/286707140-ce0cafd4-cb58-413b-86d6-cc0f1b481fd7.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MzY5MjkwMTAsIm5iZiI6MTczNjkyODcxMCwicGF0aCI6Ii8xMzUxNjI3MjAvMjg2NzA3MTQwLWNlMGNhZmQ0LWNiNTgtNDEzYi04NmQ2LWNjMGYxYjQ4MWZkNy5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjUwMTE1JTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI1MDExNVQwODExNTBaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT1kNTRkOTNkNjk1OTIzOTNjN2M3M2QzZjBiZTk2YzcyZGUxMWFkMDFjMGRiYzVkZjY2YmJmY2VlMThmMTAwOTA0JlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCJ9.AUfO0I09wZDflZhHDx6Ge6aNKY2j5nWsnayPVpl8sAE"> I don't seem to find anything about Contrastive Learning in the code! Can you tell me where contrastive learning is implemented?