Instructions to use Fhrozen/voc_fastdiff_multilingual with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use Fhrozen/voc_fastdiff_multilingual with ESPnet:
unknown model type (must be text-to-speech or automatic-speech-recognition)
- Notebooks
- Google Colab
- Kaggle
| espnet: '202207' | |
| files: | |
| model_file: exp/tts_vocoder_fastdiff/train.loss.ave_5best.pth | |
| python: "3.9.13 (main, Aug 25 2022, 23:26:10) \n[GCC 11.2.0]" | |
| timestamp: 1673910959.463416 | |
| torch: 1.12.1 | |
| yaml_files: | |
| train_config: exp/tts_vocoder_fastdiff/config.yaml | |