Audio-Text-to-Text
Transformers
Safetensors
English
Chinese
audio
speech
multimodal
audio-language-model
asr
speech-recognition
Instructions to use cslys1999/Eureka-Audio-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cslys1999/Eureka-Audio-Instruct with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("cslys1999/Eureka-Audio-Instruct", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 025aa905c7a3c7536634ce69fbc584495545e328c86c6cf427ca9062d3167e4c
- Size of remote file:
- 604 Bytes
- SHA256:
- d7fc8499cc0796efa4aa02a425c915f3e3ded8faf0b2eec29e92357cf7586c41
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.