---
title: BigVGAN_singing_bigdata
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/BigVGAN_singing_bigdata"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/BigVGAN_singing_bigdata.md"
repository: AI-ModelScope/BigVGAN_singing_bigdata
last_updated: 2023-12-20
license: mit
downloads: 42
stars: 0
---

# BigVGAN_singing_bigdata

> BigVGAN_singing_bigdata - AI-ModelScope 在 ModelScope 开源的模型。Amphion Vocoder Pretrained Models

AI-ModelScope/BigVGAN_singing_bigdata 是 ModelScope 魔搭社区上的机器学习模型，采用 mit 许可。

- **Repository**: AI-ModelScope/BigVGAN_singing_bigdata
- **License**: mit
- **Downloads**: 42
- **Stars**: 0
- **Last updated**: 2023-12-20

Source: https://www.modelscope.cn/models/AI-ModelScope/BigVGAN_singing_bigdata

---

# Amphion Vocoder Pretrained Models

We provide the a [BigVGAN](https://github.com/open-mmlab/Amphion/tree/main/egs/vocoder/gan) pretrained checkpoint for singing voice, which is trained on over 120 hours of singing voice data.

## Quick Start

To utilize these pretrained vocoders, just run the following commands:

### Step1: Download the checkpoint
```bash
git lfs install
git clone https://huggingface.co/amphion/vocoder
```

### Step2: Clone the Amphion's Source Code of GitHub
```bash
git clone https://github.com/open-mmlab/Amphion.git
```

### Step3: Specify the checkpoint's path
Use the soft link to specify the downloaded checkpoint in the first step:

```bash
cd Amphion
mkdir ckpts/vocoder
cd ckpts/vocoder
ln -s ../vocoder/bigvgan_singing ckpts/vocoder/bigvgan_singing
```

### Step4: Inference
For analysis synthesis on the processed dataset, raw waveform or predicted mel spectrograms, you can follow the inference part of [this recipe](https://github.com/open-mmlab/Amphion/blob/main/egs/vocoder/gan/tfr_enhanced_hifigan/README.md).

```bash
sh egs/vocoder/gan/tfr_enhanced_hifigan/run.sh --stage 3 \
	--infer_mode [Your chosen inference mode] \
	--infer_datasets [Datasets you want to inference, needed when infer_from_dataset] \
	--infer_feature_dir [Your path to your predicted acoustic features, needed when infer_from_feature] \
	--infer_audio_dir [Your path to your audio files, needed when infer_form_audio] \
	--infer_expt_dir Amphion/ckpts/vocoder/[YourExptName] \
	--infer_output_dir Amphion/ckpts/vocoder/[YourExptName]/result \
```

## Citaions

```bibtex
@misc{gu2023cqt,
      title={Multi-Scale Sub-Band Constant-Q Transform Discriminator for High-Fidelity Vocoder}, 
      author={Yicheng Gu and Xueyao Zhang and Liumeng Xue and Zhizheng Wu},
      year={2023},
      eprint={2311.14957},
      archivePrefix={arXiv},
      primaryClass={cs.SD}
}
```