metadata
license: cc-by-nc-nd-4.0
language:
- ko
- en
pipeline_tag: audio-to-audio
tags:
- animal
- music
https://huggingface.co/kangting87/Giant_Panda_Fu_Bao/resolve/main/Giant_Panda_(Fu_Bao)_10e_210s_best_epoch_v2.zip?download=true
Technology: RVC
Extraction Type: rmvpe
Number of Epochs: 10
Steps: 210
Model Architecture: v2
Sampling Rate: 48k
Pitch Guidance: True
Dataset Length: 1 min and 59 seconds
Overtrain Info: Smoothed loss_g 8.659 and loss_d 3.483
λ³Έ AI λͺ¨λΈμ μμλλ λλ΅ B2 μμλΆν° D5 κΉμ§μ λλ€.
λ§μ½ B2 λ³΄λ€ μλλ‘ λ΄λ €κ°κ±°λ νΉμ D5 λ³΄λ€ μλ‘ μ¬λΌκ°λ©΄, μλ¦¬κ° μμλλ νμμ΄ μμν λ°μν©λλ€.
(This AI model approximately has the vocal range of B2~D5, and if it goes below B2 or above D5, the sound damaging phenomenon gradually begins to occur.)
νΈλ°μ€ μΈμ μ리 νλ³Έμ΄ λ§μ§ μμ κ΄κ³λ‘, μν (epoch) μλ λ§€μ° μ μ΅λλ€.
(Because there are not many samples of Fu Bao's voices, the number of epochs is also quite small.)
μμ μ μ΄μ©μ κΈμ§ν©λλ€.
(Commercial use is prohibited.)