L0SG commited on
Commit
ef09b55
1 Parent(s): 008b54d
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -29,7 +29,7 @@ pipeline_tag: audio-to-audio
29
 
30
  - **Jul 2024 (v2):** We release BigVGAN-v2 along with pretrained checkpoints. Below are the highlights:
31
  - Custom CUDA kernel for inference: we provide a fused upsampling + activation kernel written in CUDA for accelerated inference speed. Our test shows 1.5 - 3x faster speed on a single A100 GPU.
32
- - Improved discriminator and loss: BigVGAN-v2 is trained using a [multi-scale sub-band CQT discriminator](https://arxiv.org/abs/2311.14957) and a [multi-scale mel spectrogram loss](https://arxiv.org/abs/2306.06546).
33
  - Larger training data: BigVGAN-v2 is trained using datasets containing diverse audio types, including speech in multiple languages, environmental sounds, and instruments.
34
  - We provide pretrained checkpoints of BigVGAN-v2 using diverse audio configurations, supporting up to 44 kHz sampling rate and 512x upsampling ratio.
35
 
 
29
 
30
  - **Jul 2024 (v2):** We release BigVGAN-v2 along with pretrained checkpoints. Below are the highlights:
31
  - Custom CUDA kernel for inference: we provide a fused upsampling + activation kernel written in CUDA for accelerated inference speed. Our test shows 1.5 - 3x faster speed on a single A100 GPU.
32
+ - Improved discriminator and loss: BigVGAN-v2 is trained using a multi-scale sub-band CQT discriminator and a multi-scale mel spectrogram loss.
33
  - Larger training data: BigVGAN-v2 is trained using datasets containing diverse audio types, including speech in multiple languages, environmental sounds, and instruments.
34
  - We provide pretrained checkpoints of BigVGAN-v2 using diverse audio configurations, supporting up to 44 kHz sampling rate and 512x upsampling ratio.
35