WebKit

Discover the powerful RVC V2 Harvest Model, specially trained on 66 crystal-clear voice clips from 'The Angry Beavers'. This model excels at creating AI music and covers, particularly with its compatibility with Harvest, but also performs exceptionally with Crepe and Mangio-Crepe for high-pitched sounds. Perfect for generating unique text-to-speech creations! Try it out for free with our AI tools. Proudly brought to you by the innovative team at Huggingface.

Trained on a dataset of 66 clear voice clips from the show ranging from about 3-10 seconds long each. Trained with and usually works best with Harvest, although on some occasions Crepe and/or Mangio-Crepe works better, especially when dealing with higher pitches. If youre going to use this model credit to me would be greatly appreciated. Huggingface Drive

Treeflower (The Angry Beavers) - Harvest

Treeflower (The Angry Beavers) - RVC V2 Harvest, 250 Epochs

AngryBeaverNerd

Trained on a dataset of 66 clear voice clips from the show ranging from about 3-10 seconds long each. Trained with and usually works best with Harvest, although on some occasions Crepe and/or Mangio-Crepe works better, especially when dealing with higher pitches.

If you’re going to use this model credit to me would be greatly appreciated.

Huggingface link: https://huggingface.co/AngryBeaverNerd/Treeflower/resolve/main/treeflower.zip
Google Drive link: https://drive.google.com/file/d/1bdWMstNiv27l9W6UOdEJQSk7PdZAmgSq/view?usp=drive_link

Examples:
https://youtu.be/A7g9AAFsfFA
https://youtu.be/p3xym1KaJg4

Trained on a dataset featuring every Norbert voice line from Nickelodeon All Star Brawl 2 lasting about a combined 6 minutes and 30 seconds long. Trained with RMVPE but I believe it'll work well with most other f0's. If you're going to use this model credit to me would be greatly appreciated. This model was supposed to be 250 epochs but Colab crapped out before it could be fully trained although thankfully I was able to extract a save with 150 epochs. I'm putting this up here for testing purposes only until I get the model fully trained.

Norbert Beaver (Nickelodeon All Star Brawl 2)

Trained on a dataset of 73 voice clips from the show ranging from about 3-10 seconds long each. Trained with RMVPE but I believe it'll work well with most other f0's. You WILL need to lower the pitch setting by -15 to -20 or else the model won't sound accurate. If you're going to use this model credit to me would be greatly appreciated.

Barry Bear (The Angry Beavers)

Trained on a dataset of 64 clear voice clips from the show ranging from about 3-10 seconds long each. Trained with and usually works best with Harvest, although on some occasions Crepe and/or Mangio-Crepe works better, especially when dealing with higher pitches. As this is my first ever AI model I may or may not make an improved version of this model someday depending on what you guys think. If youre going to use this model credit to me would be greatly appreciated. If you want a good model to use for Daggett Id recommend using s Moxxie model, link here:

Treeflower (The Angry Beavers) - Harvest

Description

Samples

Saiba Momoi (Blue Archive)

Adel imam (Egyptian Actor) عادل امام (ممثل مصري)

JP Furina / Focalors CV: Inori Minase (Genshin Impact)

Ariana Grande AI

Hu Tao JP (Genshin Impact)

JENNIE of BLACKPINK [Strong Ver.]

Saiba Momoi (Blue Archive) (VA: Tokui Sora)

Hatsune Miku

SpongeBob SquarePants (Talking And Singing)

Takanashi Hoshino (from Blue Archive)

Satoru Gojo (JJK) [VA Yuichi Nakamura]

ENHYPEN Heeseung

Sunaokami Shiroko (Blue Archive)

Goku (Mario Castañeda) (Latin American Spanish) (UPDATE)

Villager (Minecraft)

Mortis [Brawl stars]

Jungkook (BTS)

Melodie - (Brawl Stars) - (English & Korean Voices)

Tendou Arisu (Blue Archive)

Kanye West