JAX Implementation BigVGAN
Project description
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)
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
jax_bigvgan-0.0.8.tar.gz
(9.3 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file jax_bigvgan-0.0.8.tar.gz.
File metadata
- Download URL: jax_bigvgan-0.0.8.tar.gz
- Upload date:
- Size: 9.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.11.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c86fee5c312e5bf8e0c1d22cdf42dc0b7fdb6771250094edaa13fd0db19267a9
|
|
| MD5 |
f3551571a8c6c22dd9fdb132ff7054a3
|
|
| BLAKE2b-256 |
0c72e196cb3b032741088c7ba3d005b2b0e64526baefcf3edc9c0984ae2008c0
|
File details
Details for the file jax_bigvgan-0.0.8-py3-none-any.whl.
File metadata
- Download URL: jax_bigvgan-0.0.8-py3-none-any.whl
- Upload date:
- Size: 9.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.11.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9782e1367d9945122e83cf653919137c0521cc91c1cb4f22b6836be4cdfdbf3e
|
|
| MD5 |
44307736557eb0c5135883f5f3b83f80
|
|
| BLAKE2b-256 |
9a4378a4c07539f88160fab6de191337600322aa0fb96d63d4742db72431779a
|
