Instructions to use razhan/mms-tts-ckb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use razhan/mms-tts-ckb with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="razhan/mms-tts-ckb")# Load model directly from transformers import AutoTokenizer, AutoModelForTextToWaveform tokenizer = AutoTokenizer.from_pretrained("razhan/mms-tts-ckb") model = AutoModelForTextToWaveform.from_pretrained("razhan/mms-tts-ckb") - Notebooks
- Google Colab
- Kaggle
Trained model version
#1
by farzanehnakhaee70 - opened
It seems that this model is not trained. Previously I've seen razhan/mms-tts-ckb-train which was trained. However, I do not see it in the model card. Is it possible to share the trained model?
Dear Farzaneh,
This model was poorly trained on a dataset that was synthetically generated using my Whisper model. The other model only served as an initialization checkpoint for this one. Due to HF's storage quota limits for free accounts, I had to delete it.