Sir David Attenborough (Voice Model) for Retrieval based Voice ConversionSee Here: <a target="_blank" rel="ugc" href="https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/docs/README.en.md">https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/docs/README.en.md</a>You can create TTS with this app for RVC Here: <a target="_blank" rel="ugc" href="https://github.com/litagin02/rvc-tts-webui">https://github.com/litagin02/rvc-tts-webui</a>Set Index rate to 0 and protect to 0.5, use Edge TTS "en-GB-RyanNeural-Male" and Transpose to -5.Example TTS: <a target="_blank" rel="ugc" href="https://voca.ro/1cH64bMFS5dV">https://voca.ro/1cH64bMFS5dV</a>Example Live Speech: <a target="_blank" rel="ugc" href="https://voca.ro/1cOAl5uRIEOt">https://voca.ro/1cOAl5uRIEOt</a>Example Singing Version:Acapella Sample of Apashe - Dies Irae <a target="_blank" rel="ugc" href="https://voca.ro/15xjQ44knEac">https://voca.ro/15xjQ44knEac</a>Loli God Attenborough (Difficult Voice but was able to do it) <a target="_blank" rel="ugc" href="https://voca.ro/1dgVhQTADHYy">https://voca.ro/1dgVhQTADHYy</a><h1 id="heading-39">2.0 RVC TTS Notes</h1>This is the final version of 2.0 RVC for TTS and Singing.Training Info<ul><li>48K Hz</li><li>1000 Epoch, 12,000 steps</li><li>Pitch Guidance: False</li><li>Model architecture version v2</li><li>Fp16</li><li>316 hours of audio.</li></ul><h2 id="heading-13"></h2><h1 id="heading-39">2.0 RVC Singing + TTS Notes</h1>This is the final version of 2.0 RVC for TTS and Singing.Training Info<ul><li>48K Hz</li><li>1000 Epoch, 12,000 steps</li><li>Pitch Guidance: True</li><li>Model architecture version v2</li><li>Fp16</li><li>200 hours of audio</li></ul><h1 id="heading-40">1.0 Notes</h1>Training Info<ul><li>40K Hz</li><li>200 Epoch</li><li>Pitch Guidance: True</li><li>Model architecture version v2</li><li>Fp16</li><li>4 hours of audio</li><li>8 hours of my time</li></ul>

Sir David Attenborough (Voice Model)

2.0 RVC Singing + TTS NotesThis is the final version of 2.0 RVC for TTS and Singing.Training Info<ul><li>48K Hz</li><li>1000 Epoch, 12,000 steps</li><li>Pitch Guidance: True</li><li>Model architecture version v2</li><li>Fp16</li><li>200 hours of audio.</li></ul>

Files with SHA256: 05960d991a890b6e2251672a64e1d74bdcc2d1d2d50ed771e6e359d97eb6a4f1