Instructions to use Nithu/text-to-speech with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Fairseq
How to use Nithu/text-to-speech with Fairseq:
from fairseq.checkpoint_utils import load_model_ensemble_and_task_from_hf_hub models, cfg, task = load_model_ensemble_and_task_from_hf_hub( "Nithu/text-to-speech" ) - Notebooks
- Google Colab
- Kaggle
Download hifigan.json from Nithu/text-to-speech: direct link, hf CLI and curl.
- Browser
- Download file 762 Bytes
-
https://huggingface.co/Nithu/text-to-speech/resolve/main/hifigan.json
- Command line
-
hf download hf://Nithu/text-to-speech/hifigan.json
-
curl -L -o hifigan.json https://huggingface.co/Nithu/text-to-speech/resolve/main/hifigan.json
762 Bytes
| { | |
| "resblock": "1", | |
| "num_gpus": 0, | |
| "batch_size": 16, | |
| "learning_rate": 0.0002, | |
| "adam_b1": 0.8, | |
| "adam_b2": 0.99, | |
| "lr_decay": 0.999, | |
| "seed": 1234, | |
| "upsample_rates": [8,8,2,2], | |
| "upsample_kernel_sizes": [16,16,4,4], | |
| "upsample_initial_channel": 512, | |
| "resblock_kernel_sizes": [3,7,11], | |
| "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]], | |
| "segment_size": 8192, | |
| "num_mels": 80, | |
| "num_freq": 1025, | |
| "n_fft": 1024, | |
| "hop_size": 256, | |
| "win_size": 1024, | |
| "sampling_rate": 22050, | |
| "fmin": 0, | |
| "fmax": 8000, | |
| "fmax_for_loss": null, | |
| "num_workers": 4, | |
| "dist_config": { | |
| "dist_backend": "nccl", | |
| "dist_url": "tcp://localhost:54321", | |
| "world_size": 1 | |
| } | |
| } | |