Nvidia Big-VGAN jax version
This version is working perfectly fine. 😀
Original https://github.com/NVIDIA/BigVGAN
Example
from jax_bigvgan import load_model
bigvgan_model,bigvgan_params = load_model(model_type="24khz")
rng = {'params': jax.random.PRNGKey(0), 'dropout': jax.random.PRNGKey(0)}
res = jax.jit(bigvgan_model.apply)({"params":bigvgan_params},out[:,ref_len:],rngs=rng)
import soundfile as sf
sf.write("output.wav",res[0,0],samplerate=24000)
1 maintainer
Metadata
1 maintainer
Release files for jax-bigvgan 0.0.8
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| jax_bigvgan-0.0.8.tar.gz | 9.3 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| jax_bigvgan-0.0.8-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 19.0 kB
Release files / jax_bigvgan-0.0.8.tar.gz
| Download URL | jax_bigvgan-0.0.8.tar.gz |
|---|---|
| Size | 9.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c86fee5c312e5bf8e0c1d22cdf42dc0b7fdb6771250094edaa13fd0db19267a9
|
|
BLAKE2b-256 checksum How to use checksums |
0c72e196cb3b032741088c7ba3d005b2b0e64526baefcf3edc9c0984ae2008c0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.11
|
Release files / jax_bigvgan-0.0.8-py3-none-any.whl
| Download URL | jax_bigvgan-0.0.8-py3-none-any.whl |
|---|---|
| Size | 9.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
9782e1367d9945122e83cf653919137c0521cc91c1cb4f22b6836be4cdfdbf3e
|
|
BLAKE2b-256 checksum How to use checksums |
9a4378a4c07539f88160fab6de191337600322aa0fb96d63d4742db72431779a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.11
|
