vocos mlx

VOCOS - MLX

使用MLX框架實現VOCOS。 VOCOS允許從MEL頻譜圖或Encodec代幣中高質量重建音頻。

VOCOS：縮小時間域與基於傅立葉的神經聲碼編碼器之間的差距，以進行高質量音頻合成

紙[ABS] [PDF]

安裝

要在推理模式下使用VOCOS，請使用：

pip install vocos-mlx

用法

MEL頻譜圖

 from vocos_mlx import Vocos , load_audio , log_mel_spectrogram

vocos = Vocos . from_pretrained ( "lucasnewman/vocos-mel-24khz" )

# reconstruct
audio = load_audio ( "audio.wav" , 24_000 )
reconstructed_audio = vocos ( audio )

# decode from mel spec
mel_spec = log_mel_spectrogram ( audio , n_mels = 100 )
decoded_audio = vocos . decode ( mel_spec )

Eccodec

 from vocos_mlx import Vocos , load_audio

vocos = Vocos . from_pretrained ( "lucasnewman/vocos-encodec-24khz" )

# reconstruct
audio = load_audio ( "audio.wav" , 24_000 )
reconstructed_audio = vocos ( audio , bandwidth_id = 3 )

# decode with encodec codes
codes = vocos . get_encodec_codes ( audio , bandwidth_id = 3 )
decoded_audio = vocos . decode_from_codes ( codes , bandwidth_id = 3 )

欣賞

AWNI HANNUN用於MLX的參考Encodec實現。

引用

 @article{siuzdak2023vocos,
  title={Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis},
  author={Siuzdak, Hubert},
  journal={arXiv preprint arXiv:2306.00814},
  year={2023}
}

執照

該存儲庫中的代碼按照許可證文件中的MIT許可發布。