Instructions to use ixxan/mms-tts-uig-script_arabic-UQSpeech with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ixxan/mms-tts-uig-script_arabic-UQSpeech with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="ixxan/mms-tts-uig-script_arabic-UQSpeech")# Load model directly from transformers import AutoTokenizer, AutoModelForTextToWaveform tokenizer = AutoTokenizer.from_pretrained("ixxan/mms-tts-uig-script_arabic-UQSpeech") model = AutoModelForTextToWaveform.from_pretrained("ixxan/mms-tts-uig-script_arabic-UQSpeech", device_map="auto") - Notebooks
- Google Colab
- Kaggle
metadata
library_name: transformers
tags:
- mms
- vits
license: cc-by-nc-4.0
datasets:
- ixxan/mms-tts-uig-script_arabic-UQSpeech
language:
- ug
base_model:
- facebook/mms-tts
Model Card for Model ID
Model Details
Finetuned facebook/mms-tts model for Uyghur language
Training procedure
Finetuning code avaiblable in https://github.com/ixxan/ug-speech