John Oliver_v2

About John Oliver_v2 - RVC-v2 - Mangio-Crepe (32 Hop Length) - 32k sample rate - 8 batch size - 107 epochs

Model created by me (AI_Characters). Please credit me for the model creation when uploading a piece of work (song, speech, etc...) you created using this model to social media (YouTube, Instagram, etc...). I would love to know when it is used! If you want to support what I am doing, donations to my **Ko-Fi** (<https://ko-fi.com/aicharacters>) would be greatly appreciated! Those will go towards funding the renting of GPUs for further experimentation and model making. **Download:** <https://huggingface.co/ai-characters/AI-Voice-Models-by-AI_Characters/resolve/main/johnoliver_v2-12min_truncated-rvc_v2-32k-mangio32-batch8-by_AI_Characters_e107_s4066.zip> Dataset: - Source: YouTube video of the Last Week Tonight episode "Biden and the Border" - Silence truncated - Final length: 12min Training settings: - Model: RVC-v2 - Pitch extraction algorithm: Mangio-Crepe with 32 Hop Length - Target sample rate: 32k - Batch size: 8 - Epochs: 107 **Recommended inference settings:** - Pitch extraction algorithm: RMVPE - Median filtering: 3 - Search feature ratio: 0-0.5 *(higher than 0 will create a more true-to-the-character voice but also introduces more artifacts)* - Volume envelope: 0-1 *(highly depends on the song)* - Protect voiceless consonants: 0.1 **Extra notes:** I have previously created a John Oliver model here: https://discord.com/channels/1089076875999072296/1134376421104549958/1134376421104549958 However, this new one here was created using different training settings and I find it to be superior to the old one. I thus highly recommend using this new model here instead of the old one. Still, I will leave the old model up in case you prefer that one. *Any honest critique of the model is greatly appreciated! Please post such in this thread! Please also post any works you created using this model in this thread, too!*