some changes

IAHispano · Apr 19, 2024 · 8ef9288 · 8ef9288
1 parent a5fed25
commit 8ef9288
Show file tree

Hide file tree

Showing 7 changed files with 21 additions and 13 deletions.
diff --git a/Beginners/Interface.md b/Beginners/Interface.md
@@ -17,3 +17,5 @@ One of the main features of applio for user comfort is a simple to understand in
 - **How to use and understand the Tensorboard:**[Tensorboard Guide](/get-started/tensorboard)
 
 - **Use the Audio Analyzer Tool for your datasets:** [Audio Analyzer Guide](/get-started/audio-analyzer/)
+
+- **Combine models to create a new one:** [Voice Blender Guide](/get-started\Voice-Blender.md)
diff --git a/assets/Applio_Website.png b/assets/Applio_Website.png
diff --git a/assets/applio_bot.png b/assets/applio_bot.png
diff --git a/faq/rvc/rvc.md b/faq/rvc/rvc.md
@@ -9,7 +9,7 @@ order: C
 Questions about RVC.
 
 ==- What is RVC?
-RVC (Retrieval-Based Voice Conversion) is one of the is one of the Ai voice cloning techniques using speech synthesis.
+RVC (Retrieval-Based Voice Conversion) is an advanced AI voice cloning techniques using speech synthesis.
 ==- 
 ==- What are the requirements for RVC/Applio?
 The minimum required for local training is an Nvidia RTX series 20 graphics card with 8GB of VRAM to train models, in the case of inference you only need to have a decent CPU and at least 4GB of VRAM. If you have a Celeron processor, it would be better to look at [other alternatives](/get-started\Alternatives.md).

diff --git a/get-started/pretrained.md b/get-started/pretrained.md
@@ -60,6 +60,12 @@ Works well with Russian datasets and also helps models of other languages to pro
 
 Works well with Russian or Japanese language datasets and also helps models of other languages to pronounce Russian or Japanese well. This only supports **40k** sample rate.
 
-Make sure to select the sample rate according to the sample rate of the custom pretraineds.
-
 > https://huggingface.co/MUSTAR/SnowieV3.1-X-RinE3-40K/tree/main
+
+### KLM v7 by SeoulStreamingStation
+
+Works well with Korean and some types of Japanese voices. Unlike typical pre-trained models, it has a very wide vocal range, which should be very helpful for those covering songs, this only supports **32k** sample rate.
+
+> **32K**: https://huggingface.co/SeoulStreamingStation/KLMv7s/resolve/main/KLMv7s_32k.zip
+
+Make sure to select the sample rate according to the [sample rate](https://docs.applio.org/guides/datasets/sample-rate/#what-is-sample-rate) of the custom pretraineds.
diff --git a/guides/Audio/Karafan.md b/guides/Audio/Karafan.md
@@ -40,9 +40,6 @@ On Windows 11, you must allow first the execution of the **BAT file**:
 
 6. Now, you can launch **KaraFan.pyw** by double-clicking on it.
 
-## How To Update?
-Simply **Run the Setup.py** file !
-
 ### STRUCTURE 📂
 After installation, you'll find new folders at the root of the folder you have chosen with the following structure :
 
@@ -56,19 +53,22 @@ Folder | Function
 / Results | Here you will find your extracted audio files (or another one)
 
 ## How To Use?
-1. Place your audio in the **music folder** and copy the **path of your song** that you want to separate and the path of the **folder** where the separated song will be stored.
+1. Place your audio in the **Music folder** and copy the **path of your song** that you want to separate and the path of the **folder** where the separated song will be stored.
 
 2. Now place the settings you want to apply, try the ones you want the most, but if you want to effectively separate the instrumental or sounds from the vocals, I recommend the following settings:
 
-||| To effectively separate the instrumental from the vocals
+||| To separate the instrumental from the vocals
 ![](../../assets/Musica.png)
-||| In case you want to separate the voice from a YouTuber’s video or other typoe of video
+||| To separate other typoe of audios
 ![](../../assets/Youtuber.png)
 |||
 
 3. We click on **Start** and it will begin to separate the chosen song. At the end of the process, the message **Processing DONE** will appear at the end of the interface.
 
-4. Now we go to the **Vocals** folder and we will find a folder with the name of our song or audio. There we will find a list of audios, we download the audio with the name **Vocal Final**, in case you want the instrumental one that says **Music Final**.
+4. Now we go to the **Results** folder and we will find a folder with the name of our song or audio. There we will find a list of audios, we download the audio with the name **Vocal Final**, in case you want the instrumental one that says **Music Final**.
+
+## How To Update?
+Simply **Run the Setup.py** file!
 
 For more information, visit the [GitHub repository](https://github.com/Captain-FLAM/KaraFan).
 +++ Google Colab
@@ -87,9 +87,9 @@ The Colab only lasts 30 minutes in execution. Additionally, it is possible that
 
 6. Now place the settings you want to apply, try the ones you want the most, but if you want to effectively separate the instrumental or sounds from the vocals, I recommend the following settings:
 
-||| To effectively separate the instrumental from the vocals
+||| To separate the instrumental from the vocals
 ![](../../assets/Musica.png)
-||| In case you want to separate the voice from a YouTuber’s video or other typoe of video
+||| To separate other type of audios
 ![](../../assets/Youtuber.png)
 |||
 

diff --git a/voice-models/Bot.md b/voice-models/Bot.md
@@ -15,4 +15,4 @@ The bot is capable of searching models within a database of over +500k functiona
 
 Type the command /search, enter the model name you want to search for, Click on **📤Download** to download the model or right click to get the model link, that’s all.
 
-![](../assets/Applio_Bot.png)
+![](/assets\Applio_Bot.png)