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
| # Utility Scripts | |
| - `summarize_lr_showcase.py`: summarize one experiment output directory into `showcase_report.md`. | |
| - `summarize_threshold_sweep.py`: summarize threshold-sweep JSON/log outputs. | |
| - `write_full_asr_experiment_report.py`: build the paper-facing multilingual/English report from existing result folders. | |
| - `analysis/per_sample_difficulty.py`: per-sample difficulty analysis used for the paper discussion. | |
| - `hparam/search_alpha.sh`: legacy alpha/tolerance grid search helper. | |