Instructions to use myshell-ai/MeloTTS-Korean with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use myshell-ai/MeloTTS-Korean with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="myshell-ai/MeloTTS-Korean")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("myshell-ai/MeloTTS-Korean", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add new speakers
#1
by youngandbin - opened
Looking at the config.json, seems like there is only one speaker available.
Can we add some more custom speakers in this model?
"data": {
"sampling_rate": 44100,
"filter_length": 2048,
"hop_length": 512,
"add_blank": true,
"n_speakers": 256,
"spk2id": {
"KR": 0
}