From dc375c7f448053cc47399d5c0503673de9f45569 Mon Sep 17 00:00:00 2001 From: Julian Jocque Date: Sat, 11 Jan 2025 18:42:09 -0600 Subject: [PATCH] Update README.md Fix inaccurate wording --- egs/vocoder/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/egs/vocoder/README.md b/egs/vocoder/README.md index 9d247d2f..9883cc2e 100644 --- a/egs/vocoder/README.md +++ b/egs/vocoder/README.md @@ -6,7 +6,7 @@ We provide a [**beginner recipe**](gan/tfr_enhanced_hifigan/README.md) to demons ## Supported Models -Neural vocoder generates audible waveforms from acoustic representations, which is one of the key parts for current audio generation systems. Until now, Amphion has supported various widely-used vocoders according to different vocoder types, including: +Neural vocoder generates audible waveforms from acoustic representations, which is one of the key parts for current audio generation systems. Amphion supports various widely-used vocoders according to different vocoder types, including: - **GAN-based vocoders**, which we have provided [**a unified recipe**](gan/README.md) : - [MelGAN](https://arxiv.org/abs/1910.06711) @@ -20,4 +20,4 @@ Neural vocoder generates audible waveforms from acoustic representations, which - [Diffwave](https://arxiv.org/abs/2009.09761) - **Auto-regressive based vocoders** (👨‍💻 developing): - [WaveNet](https://arxiv.org/abs/1609.03499) - - [WaveRNN](https://arxiv.org/abs/1802.08435v1) \ No newline at end of file + - [WaveRNN](https://arxiv.org/abs/1802.08435v1)