How to use microsoft/speecht5_tts with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="microsoft/speecht5_tts")
# Load model directly from transformers import AutoProcessor, AutoModelForTextToSpectrogram processor = AutoProcessor.from_pretrained("microsoft/speecht5_tts") model = AutoModelForTextToSpectrogram.from_pretrained("microsoft/speecht5_tts")
The example in the model card is broken in at least one way:
You'll need to restart the runtime for sentencepiece to be recognized.
Thank you, that worked! I'll try and send a PR once I get it running.
· Sign up or log in to comment
