Instructions to use microsoft/speecht5_vc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/speecht5_vc with Transformers:
# Load model directly from transformers import AutoProcessor, SpeechT5ForSpeechToSpeech processor = AutoProcessor.from_pretrained("microsoft/speecht5_vc") model = SpeechT5ForSpeechToSpeech.from_pretrained("microsoft/speecht5_vc") - Notebooks
- Google Colab
- Kaggle
Fix config files
#2
by Matthijs - opened
No description provided.
I made changes to the code to support fine-tuning (ASR and TTS only), which required changes to the config files. Notably the tokenizer needs to have the mask and ctc_blank tokens, even if not used during inference.
Matthijs changed pull request status to open
nielsr changed pull request status to merged