mah92/hifigan_for_sherpa

بسم الله

1. Converted universal v1, v2, v3 22050Hz hifigan models from here and here

2. Converted to onnx using this

3. Added metadata as such using the above python script: {'model_type': 'hifigan', 'model_filename': 'hifigan_universal_22050hz_v1', 'sample_rate': 22050, 'version': 1, 'model_author': 'jik876', 'maintainer': 'k2-fsa', 'dataset': 'Universal', 'url1': 'https://github.com/jik876/hifi-gan', 'url2': ''}

Note1: hifigan v2 is much smaller, faster and with lower memory need

Note2: As LJ speech is a female single speaker dataset, hifigan based on it does not work well on men's voice. vctk models work well for both genders.

Conclusion: Use vctk_v2!