Downloads · 30 days
23
8% of all-time downloads
hifigan-ar-v2
muhtasham/hifigan-ar-v2
hifigan-ar-v2 is a machine learning model from muhtasham. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
A standalone implementation of HiFiGAN vocoder for Arabic text-to-speech, based on the paper "HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis" (https://arxiv.org/pdf/2010.056…
All-time downloads
275
Public
Repo size
3.5 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.ckpt55.8 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Mar 27, 2025
- Updated
- Apr 1, 2025
- SHA
- 9d199d5c
Model card
From the Hugging Face model README
HiFiGAN Arabic Vocoder
A standalone implementation of HiFiGAN vocoder for Arabic text-to-speech, based on the paper "HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis" (https://arxiv.org/pdf/2010.05646.pdf).
Usage
from hifigan_ar_v2 import HiFiGANArabicGenerator
import torch
# Load the model
model = HiFiGANArabicGenerator.from_pretrained("generator.ckpt", "config.json")
# Generate audio from mel spectrogram
mel = torch.rand(1, 80, 122) # Example mel spectrogram
audio = model(mel) # Shape: [1, 1, 8448]
Model Details
- Sample Rate: 22050 Hz
- Input: Mel spectrogram (80 channels)
- Output: Audio waveform (1 channel)
- License
- mit
- Languages
- en
- Created
- Mar 27, 2025
- Updated
- Apr 1, 2025