Instructions to use MBZUAI/speecht5_tts_clartts_ar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MBZUAI/speecht5_tts_clartts_ar with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="MBZUAI/speecht5_tts_clartts_ar")# Load model directly from transformers import AutoProcessor, AutoModelForTextToSpectrogram processor = AutoProcessor.from_pretrained("MBZUAI/speecht5_tts_clartts_ar") model = AutoModelForTextToSpectrogram.from_pretrained("MBZUAI/speecht5_tts_clartts_ar", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Error !
#1
by LioSolo - opened
error when running the model using the snippet code in model card :
in transformers\models\speecht5\modeling_speecht5.py , line 677
in _consistent_dropout
return torch.where(all_masks == 1, inputs_embeds, 0) * 1 / (1 - p)
RuntimeError: expected scalar type float but found __int64