Automatic Speech Recognition
Transformers
asr
speaker-diarization
timestamps
quantization
low-bit
arm
on-device
Instructions to use yongyizang/TinyMOSS-Diarize with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yongyizang/TinyMOSS-Diarize with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="yongyizang/TinyMOSS-Diarize")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("yongyizang/TinyMOSS-Diarize", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| """Deployment export and reload helpers for the fixed MOSS quantized topology.""" | |
| from importlib import import_module | |
| from typing import Any | |
| __all__ = [ | |
| "build_export_plan", | |
| "export_model", | |
| "load_export", | |
| "rebuild_cpu_model", | |
| "verify_export", | |
| ] | |
| def __getattr__(name: str) -> Any: | |
| """Load public helpers lazily so ``python -m export.export_model`` is clean.""" | |
| if name not in __all__: | |
| raise AttributeError(name) | |
| return getattr(import_module(".export_model", __name__), name) | |