Instructions to use fav-kky/SpeechT5-base-cs-tts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fav-kky/SpeechT5-base-cs-tts with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="fav-kky/SpeechT5-base-cs-tts")# Load model directly from transformers import AutoProcessor, AutoModelForTextToSpectrogram processor = AutoProcessor.from_pretrained("fav-kky/SpeechT5-base-cs-tts") model = AutoModelForTextToSpectrogram.from_pretrained("fav-kky/SpeechT5-base-cs-tts", device_map="auto") - Notebooks
- Google Colab
- Kaggle
usage under COmfyUI with F5-TTS node
Hello,
how is possible to use your model with ComfyUI at T5-TTS node? I try it , but I got errors . Also here missing vocab.TXT file, where is a table numbers-letters. Could you please give me info regards that? Thank you. Patrik
I looking for similar model like here:
https://huggingface.co/petercheben/F5_TTS_Slovak/tree/main
Hi Patrik,
I'm afraid you are searching for models with a different architecture. This model is "SpeechT5" (https://arxiv.org/abs/2110.07205), and what you are referencing is "F5-TTS" (https://arxiv.org/abs/2410.06885).
The architecture of this SpeechT5 model follows the original model https://huggingface.co/microsoft/speecht5_tts, that do not contain any vocab.TXT file either.
And please note that this is only a pre-trained model, which should be fine-tuned first.
If you have any questions, let me know.
Best, Jan