Audio-Text-to-Text
Transformers
Safetensors
Chinese
English
edgeinstant
feature-extraction
audio
speech-recognition
speech-translation
audio-question-answering
custom_code
Instructions to use chenjz24/EdgeIn-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use chenjz24/EdgeIn-v1 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("chenjz24/EdgeIn-v1", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download sequence.py from chenjz24/EdgeIn-v1: direct link, hf CLI and curl.
- Browser
- Download file 146 Bytes
-
https://huggingface.co/chenjz24/EdgeIn-v1/resolve/main/sequence.py
- Command line
-
hf download hf://chenjz24/EdgeIn-v1/sequence.py
-
curl -L -o sequence.py https://huggingface.co/chenjz24/EdgeIn-v1/resolve/main/sequence.py
146 Bytes
| """Actions reported by native-token speech generation.""" | |
| from enum import IntEnum | |
| class Action(IntEnum): | |
| READ = 0 | |
| EMIT = 1 | |
| END = 2 | |