Voice Models v2
EasyAIVoice ↗
32,019 Verified Open Models 28,884 Multi-Pitch Audition Ready 100% Direct Source URLs (HF · Drive · MEGA)
KLM v7s Batch II
RVC v2

KLM v7s Batch II

PRE-TRAINED MODEL

RVC v2 Added Apr 22, 2024
Open Model Weights Vault · Hosted on Hugging Face
Auto-Repaired Mirror Active
https://huggingface.co/SeoulStreamingStation/KLMv7s/resolve/main/KLMv7s_Batch2.zip%3Fdownload%3Dtrue?download=true
Original uploaded URL returned HTTP 404 (huggingface.co/SeoulStreamingStation/…/KLMv7s_Batch2.zip) — automatically resolved to verified archive mirror above.
Download Raw Weights (.zip) ↗
Convert Audio with This Voice in EasyAIVoice
Carries this exact model URL and your selected pitch (0 st) into the cloud studio.
Zero GPU Setup
Audio Decision Loop · Sample Deck

Audition Across 18 Pitch References

Click any semitone cell below to hear how this voice performs on female and male reference vocals and lock your preferred pitch.

0 Reference Previews
Reference Audio Previews Are Queued

Our worker is generating the 18-pitch reference samples for this model. You can already use this model immediately in EasyAIVoice or download the raw weights from Hugging Face.

Run Model in EasyAIVoice Now →
CLAP Semantic Analysis · Voice Accords

Sonic Profile at Selected Pitch

Acoustic traits measured directly from the generated output sample. Switch pitches in the Sample Deck to see how timbre shifts.

Technical Profile

Architecture: RVC v2 · Source Host: Hugging Face

Auditory Discovery · Close Alternatives

Voices That Sound Like KLM v7s Batch II

Close but not quite the right fit? Audition nearby candidates matched by vocal embedding and timbre.

High-clarity female voice
MALE · 0 st 5.13 MOS HF
High-clarity female voice
FEMALE · 0 st 5.12 MOS Direct
High-clarity female voice
FEMALE · 0 st 5.11 MOS HF
Libby Rue Better Nate Than Ever
High-clarity female voice
FEMALE · 0 st 5.10 MOS HF
Gallica Metaphor ReFantazio
High-clarity female voice
FEMALE · 0 st 5.10 MOS HF
High-clarity female voice
MALE · 0 st 5.09 MOS HF
Model Documentation & Notes

About KLM v7s Batch II (PRE-TRAINED MODEL)

This is Batch 2 of the KLM7 share version, a pre-trained Korean language model. It has been tested on Applio and comes with pre-trained models at RVC v2 / RVMPE / 32k, 40k, and 48k. It is compatible with all tools that can utilize pre-trained models for discriminators and generators, though it has been specifically tested with Applio. To use it, decompress the data in the folder where Applio is installed, under rvc\pretraineds\pretraineds_custom. While KLM can be used for languages other than Korean, it contains the most information for Korean, particularly based on vocal-related data. P.S.: Do not treat KLM as a magical tool. Always monitor the training process through TensorBoard to ensure it is sufficient. It helps to prepare the cleanest and most ideal source of data by organizing as much of the dataset as possible beforehand. The more detailed and clean the source you use, the more detail you can preserve. If you have a 10-minute dataset, and you can prepare a high-quality 5-minute subset, use that 5-minute data, but it will require considerable effort to make the most of those 5 minutes. I recommend conducting various tests based on discussions among many AI hubbers in channels like model maker 한국어 사전학습모델인 KLM7 쉐어버전의 배치2 입니다. Applio 에서 테스트 되었으며 RVC v2 / RVMPE / 32k, 40k, 48k 사전모델이 준비되어 있습니다. 차별자와 생성자를 사전학습 모델로 이용할 수 있는 모든 툴에서 이용이 가능하지만 Applio에서 테스트 되었습니다. 압축된 데이터를 Applio가 설치되어 있는 폴더 안 rvc\pretraineds\pretraineds_custom 에 압축을 풀어준 후 이용하시면 됩니다. KLM은 영어 외 다른 국가의 언어의 이용도 가능하지만 한국어에 가장 많은 정보를 담고 있고 특히 보컬과 관련된 데이터를 기반에 두고 있습니다. 추신 : KLM을 마법의 도구로 사용하지 마십시오. 텐서보드와 모니터링을 통해 충분한 학습이 이뤄지는지 항시 지켜보아야 하며 가능한 할 수 있는 만큼의 최대한의 데이터셋 정리를 사전에 하여 가장 클린하고 이상적인 소스를 이용하면 할수록 더 많은 디테일을 살릴 수 있게 도울 것입니다. (똥을 아무리 이쁘게 꾸며도 이쁜 똥이 되는 근본적인 법칙을 무시할 수 없습니다.) 10분짜리 데이터셋이 있다고 가정할때 최고의 퀄리티로 5분짜리 데이터셋을 준비할 수 있다면 그 5분의 데이터를 이용하시되 그 5분을 살리기 위해 적지 않은 노력을 하셔야 합니다. model maker 채널등을 통해 많은 AI huber들이 토론하는 내용을 토대로 다양한 테스트를 해보시길 권장드립니다. Batch 1 : 10 Actors and Vocalist's Voice, Vocal Data Batch 2 : 22 Actors and Vocalist's Voice, Vocal Data Model Link - https://huggingface.co/SeoulStreamingStation/KLMv7s/resolve/main/KLMv7s_Batch2.zip?download=true

Provenance & Open Access
Catalog ID:#27025
Weights Host:Hugging Face
Rights & Safety: Report / Takedown