Instructions to use facebook/mms-tts-bcc-script_arabic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/mms-tts-bcc-script_arabic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="facebook/mms-tts-bcc-script_arabic")# Load model directly from transformers import AutoTokenizer, AutoModelForTextToWaveform tokenizer = AutoTokenizer.from_pretrained("facebook/mms-tts-bcc-script_arabic") model = AutoModelForTextToWaveform.from_pretrained("facebook/mms-tts-bcc-script_arabic") - Notebooks
- Google Colab
- Kaggle
Update README.MD
#1
by faisaljan - opened
To save output in a Wav file, Scipy requires it to be a numpy array. Therefore, we first need to convert Pytorch tensor to a numpy array, then we can save the audio file.