ZeroRVC
Run Retrieval-based Voice Conversion training and inference with ease.
Features
- Dataset Preparation
- Hugging Face Datasets Integration
- Hugging Face Accelerate Integration
- Trainer API
- Inference API
- Index Support
- Tensorboard Support
- FP16 Support
Dataset Preparation
ZeroRVC provides a simple API to prepare your dataset for training. You only need to provide the path to your audio files. The feature extraction models will be downloaded automatically, or you can provide your own with the hubert and rmvpe arguments.
from datasets import load_dataset
from zerorvc import prepare, RVCTrainer
dataset = load_dataset("my-audio-dataset")
dataset = prepare(dataset)
trainer = RVCTrainer(
"my-rvc-model",
dataset_train=dataset["train"],
dataset_test=dataset["test"],
)
trainer.train(epochs=100, batch_size=8, upload="someone/rvc-test-1")
Inference
ZeroRVC provides an easy API to convert your voice with the trained model.
from zerorvc import RVC
import soundfile as sf
rvc = RVC.from_pretrained("someone/rvc-test-1")
samples = rvc.convert("test.mp3")
sf.write("output.wav", samples, rvc.sr)
1 maintainer
Metadata
1 maintainer
Release files for zerorvc 0.0.19
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| zerorvc-0.0.19.tar.gz | 35.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| zerorvc-0.0.19-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 80.7 kB
Release files / zerorvc-0.0.19.tar.gz
| Download URL | zerorvc-0.0.19.tar.gz |
|---|---|
| Size | 35.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0b6c2f15e80584f2e9770674bf2866e69d0abf4cbdd39153679b930972545d73
|
|
BLAKE2b-256 checksum How to use checksums |
d060ddc09c0da0adb54c92ceef60b0ec3f4ad7b2f8cc6c76960bfdc2db7b09af
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.10.0
|
Release files / zerorvc-0.0.19-py3-none-any.whl
| Download URL | zerorvc-0.0.19-py3-none-any.whl |
|---|---|
| Size | 44.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
846bc791989f37cfee8bbc36ac4bf148d66e0d9b4ec8106fa164dca8f6bd9638
|
|
BLAKE2b-256 checksum How to use checksums |
fece6473e118809d64de51d8ecb8b1079655a2c37d5d5a76a84a9b1d90bbb04e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.10.0
|
