Instructions to use frankyoujian/EdgeASR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- K2
How to use frankyoujian/EdgeASR with K2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download FFASR.md from frankyoujian/EdgeASR: direct link, hf CLI and curl.
- Browser
- Download file 2.04 kB
-
https://huggingface.co/frankyoujian/EdgeASR/resolve/main/FFASR.md
- Command line
-
hf download hf://frankyoujian/EdgeASR/FFASR.md
-
curl -L -o FFASR.md https://huggingface.co/frankyoujian/EdgeASR/resolve/main/FFASR.md
FFASR offline evaluation
EdgeASR is an offline/non-streaming English Zipformer RNN-T model. It processes the whole recording with a non-causal encoder. Do not select Streaming ASR for this model.
Submission fields
- Model ID:
frankyoujian/EdgeASR - Task: offline ASR (
asrin the API). - Extra Python requirements: copy the non-comment lines of
requirements.txt. - Setup script: leave empty.
- Custom evaluator: copy all of
ffasr_custom_evaluator.py. - Contact email: provide your own email directly to FFASR; it is not in this repo.
- Base model: fill only if applicable to the training history.
The custom evaluator pins runtime revision 496a1127c8dd4420e6934f7790cb1ddb33af13b4. The evaluator loads
the model once, uses FP32 and greedy RNN-T decoding with one symbol per encoder
frame, and exposes the loaded model for parameter counting. Batch size is 1.
There is no external LM or dataset-specific prompt/decoding configuration.
Transcript formatting
After BPE reconstruction, <cap> capitalizes the preceding word, <upp>
uppercases it, and <.>, <,>, <?> become punctuation. Formatting tags are
removed after applying their effects. FFASR applies its own WER normalization
after receiving the formatted transcript.
we <cap> are from us <upp> <,> and they are from china <cap> <.> who <cap> are they from <?>
We are from US, and they are from China. Who are they from?
Reproducibility and validation
artifact_manifest.json records SHA-256 hashes of the unchanged checkpoint,
token table, BPE model, configuration, formatter, dependencies and source.
The source snapshot retains its original license under source/LICENSE.
Sixteen formatter and production text-return tests passed during preparation, including actual model token IDs and the exact example above. Dependencies were resolved for Linux x86-64 / Python 3.12 / CUDA 12.4. Native GPU inference was not executed as part of package preparation. This document makes no claim of an official FFASR result.