init

f5/charactr/vocos-mel-24khz/.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

f5/charactr/vocos-mel-24khz/README.md

@@ -0,0 +1,71 @@
+---
+license: mit
+---
+
+# Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
+
+[Audio samples](https://charactr-platform.github.io/vocos/) |
+Paper [[abs]](https://arxiv.org/abs/2306.00814) [[pdf]](https://arxiv.org/pdf/2306.00814.pdf)
+
+Vocos is a fast neural vocoder designed to synthesize audio waveforms from acoustic features. Trained using a Generative
+Adversarial Network (GAN) objective, Vocos can generate waveforms in a single forward pass. Unlike other typical
+GAN-based vocoders, Vocos does not model audio samples in the time domain. Instead, it generates spectral
+coefficients, facilitating rapid audio reconstruction through inverse Fourier transform.
+
+## Installation
+
+To use Vocos only in inference mode, install it using:
+
+```bash
+pip install vocos
+```
+
+If you wish to train the model, install it with additional dependencies:
+
+```bash
+pip install vocos[train]
+```
+
+## Usage
+
+### Reconstruct audio from mel-spectrogram
+
+```python
+import torch
+
+from vocos import Vocos
+
+vocos = Vocos.from_pretrained("charactr/vocos-mel-24khz")
+
+mel = torch.randn(1, 100, 256)  # B, C, T
+audio = vocos.decode(mel)
+```
+
+Copy-synthesis from a file:
+
+```python
+import torchaudio
+
+y, sr = torchaudio.load(YOUR_AUDIO_FILE)
+if y.size(0) > 1:  # mix to mono
+    y = y.mean(dim=0, keepdim=True)
+y = torchaudio.functional.resample(y, orig_freq=sr, new_freq=24000)
+y_hat = vocos(y)
+```
+
+## Citation
+
+If this code contributes to your research, please cite our work:
+
+```
+@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}
+}
+```
+
+## License
+
+The code in this repository is released under the MIT license.

f5/charactr/vocos-mel-24khz/config.yaml

@@ -0,0 +1,24 @@
+feature_extractor:
+  class_path: vocos.feature_extractors.MelSpectrogramFeatures
+  init_args:
+    sample_rate: 24000
+    n_fft: 1024
+    hop_length: 256
+    n_mels: 100
+    padding: center
+
+backbone:
+  class_path: vocos.models.VocosBackbone
+  init_args:
+    input_channels: 100
+    dim: 512
+    intermediate_dim: 1536
+    num_layers: 8
+
+head:
+  class_path: vocos.heads.ISTFTHead
+  init_args:
+    dim: 512
+    n_fft: 1024
+    hop_length: 256
+    padding: center