TITAN is a state-of-the-art pretrained model designed for Retrieval-based Voice Conversion ( training. It offers a robust solution for transforming voice characteristics from one speaker to another, providing...
Model source
Source excerpt
TITAN is a state-of-the-art pretrained model designed for Retrieval-based Voice Conversion ( training. It offers a robust solution for transforming voice characteristics from one speaker to another, providing...
Sources
1 sourceVerified Sep 12
Model artifacts
9 artifactsSource excerpts
2 excerptsmodels/medium/32k/pretrained/G-f032k-TITAN-Medium.pth
pth · 423 MB · SHA-256 0f445603cc79…80b1 · Hugging Face
Downloadmodels/medium/40k/model/f040k-Titan-Medium.pth
pth · 52.7 MB · SHA-256 ac66995fcc80…1567 · Hugging Face
Downloadmodels/medium/40k/pretrained/D-f040k-TITAN-Medium.pth
pth · 817 MB · SHA-256 bc804da752ba…5ad1 · Hugging Face
Downloadmodels/medium/40k/pretrained/G-f040k-TITAN-Medium.pth
pth · 418 MB · SHA-256 217de2fd349f…924d · Hugging Face
Downloadmodels/medium/48k/model/f048k-Titan-Medium.pth
pth · 54.9 MB · SHA-256 af95c67dbfff…909d · Hugging Face
Downloadmodels/medium/48k/pretrained/D-f048k-TITAN-Medium.pth
pth · 817 MB · SHA-256 4999a5b66aec…bc44 · Hugging Face
Downloadmodels/medium/48k/pretrained/G-f048k-TITAN-Medium.pth
pth · 431 MB · SHA-256 51a6dc93687f…e153 · Hugging Face
Download--- license: apache-2.0 language: - en tags: - ai - rvc - vc - voice-cloning - applio - titan - pretrained base_model: lj1995/VoiceConversionWebUI datasets: - blaise-tk/TITAN-Medium pipeline_tag: audio-to-audio --- # TITAN: A Versatile, Robust, and High-Quality Pretrained Model for Retrieval-based Voice Conversion (RVC) Training ## Overview TITAN is a state-of-the-art pretrained model designed for Retrieval-based Voice Conversion (https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/) training. It offers a robust solution for transforming voice characteristics from one speaker to another, providing high-quality results with minimal training effort. ## Model Details ### Titan-Medium - Training Environment: Utilized a RTX 3060 TI on Applio v3.1.1 (https://github.com/IAHispano/Applio), employing a batch size of 8 over a span of 3 weeks. - Iterations (48k): 1018660 Steps and 530 Epochs - Iterations (40k): 1010588 Steps and 467 Epochs - Iterations (32k): 1001469 Steps and 463 Epochs - Sampling rate: 48k, 40k, 32k - Fine-tuning Process: RVC v2 pretrained with pitch guidance, leveraging an 11.15-hour dataset sourced from Expresso (https://arxiv.org/abs/2308.05725) also available on [datasets/blaise-tk/TITAN-Medium](https://huggingface.co/datasets/blaise-tk/TITAN-Medium). #### Samples *Tests performed with a premature ckpt at ~700k steps doing all tests under the same conditions.* <table style="width:100%; text-align:center;"> <tr> <th>Titan-Medium</th> <th>Ov2</th> <th>Ov2.1</th> </tr> <tr> <td> <audio controls> <source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 1 - Test 1 - Titan.wav?download=true" type="audio/wav"> Your browser does not support the audio element. </audio> </td> <td> <audio controls> <source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 1 - Test 1 - Ov2.wav?download=true" type="audio/wav"> Your browser does not support the audio element. </audio> </td> </tr> </tr> <tr> <td> <audio controls> <source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 1 - Test 2 - Titan.wav?download=true" type="audio/wav"> Your browser does not support the audio element. </audio> </td> <td> <audio controls> <source src="https://huggingface.co/blaise-tk/TITAN/resolve/main/demos/Model 1 - Test 2 - Ov2.wav?download=true" type="audio/wav"...
Source context: 13 downloads · 0 likes · Pipeline audio-to-audio · Repo Anonlestia/TITAN-rvc-pretrain