Instructions to use xTorch8/mms-id-asr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use xTorch8/mms-id-asr with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="xTorch8/mms-id-asr")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("xTorch8/mms-id-asr") model = AutoModelForCTC.from_pretrained("xTorch8/mms-id-asr") - Notebooks
- Google Colab
- Kaggle
xTorch8/mms-id-asr
Model Details
Model Description
- Developed by: Evan Santosa, Alexander Brian Susanto, Kelson, Henry Wunarsa
- Model type: Automatic Speech Recognition (ASR)
- Language(s) (NLP): Indonesian (id)
- Finetuned from model: facebook/mms-1b-all
Model Sources
- Repository: GitHub Repository
Uses
Direct Use
The model is used for Automatic Speech Recognition (ASR) for Indonesian language.
Out-of-Scope Use
Even though the model is fine-tuned using the Indonesian language, the model still can perform well on languages that use alphabetic characters, such as English. However, the model will not work well for languages that not use alphabetic characters, such as Chineese, Arabic, Korean, etc, due to the fine-tuned process.
- Downloads last month
- 15
Model tree for xTorch8/mms-id-asr
Base model
facebook/mms-1b-all