Instructions to use facebook/mms-tts-udm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/mms-tts-udm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="facebook/mms-tts-udm")# Load model directly from transformers import AutoTokenizer, AutoModelForTextToWaveform tokenizer = AutoTokenizer.from_pretrained("facebook/mms-tts-udm") model = AutoModelForTextToWaveform.from_pretrained("facebook/mms-tts-udm") - Notebooks
- Google Colab
- Kaggle
The program is not working
#1
by pzxu - opened
The google collab book said the command is wrong, what is happening
with torch.no_grad():
output = model(**inputs).waveform
If you have AttributeError: 'torch.dtype' object has no attribute 'kind'
there is solution https://huggingface.co/facebook/mms-tts-fra/discussions/1