| --- |
| license: mit |
| --- |
| |
| # Amphion Vocoder Pretrained Models |
|
|
| We provide a [DiffWave](https://github.com/open-mmlab/Amphion/tree/main/egs/vocoder/diffusion) pretrained checkpoint, which is trained on 125 hours of speech data and 80 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/diffwave |
| ``` |
|
|
| ### 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 -p ckpts/vocoder |
| ln -s "$(realpath ../diffwave/diffwave)" pretrained/diffwave |
| ``` |
|
|
| ### 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/tree/main/egs/vocoder/diffusion). |
|
|
| ```bash |
| sh egs/vocoder/diffusion/diffwave/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 \ |
| ``` |
