Automatic Speech Recognition
Transformers
qwen3-asr
latent-reasoning
test-time-compute
parameter-efficient
Instructions to use voidful/latentASR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use voidful/latentASR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="voidful/latentASR")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("voidful/latentASR", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Hugging Face Release
The public model repo is intended to be:
voidful/latentASR
The repository hosts:
- LatentASR code
- adapter checkpoint
- documentation
- model card
- reproducibility outputs
Upload
From this project root:
python hf_upload/upload_to_hf.py --repo-id voidful/latentASR
The script creates the model repo if needed and uploads the current folder.
Download Checkpoint Programmatically
from huggingface_hub import hf_hub_download
ckpt = hf_hub_download(
repo_id="voidful/latentASR",
filename="checkpoints/latentASR_adapter.pth",
)
print(ckpt)